diff --git "a/experiment/maml_trainer_3/debug.log" "b/experiment/maml_trainer_3/debug.log" new file mode 100644--- /dev/null +++ "b/experiment/maml_trainer_3/debug.log" @@ -0,0 +1,24002 @@ +2025-04-03 16:31:12 | [maml_trainer] Logging to /home/h2khalil/MetaRL-Assistive-Robotics/data/local/experiment/maml_trainer_3 +2025-04-03 16:39:16 | [maml_trainer] Obtaining samples... +2025-04-03 17:02:25 | [maml_trainer] epoch #0 | Sampling for adapation and meta-testing... +2025-04-03 17:06:20 | [maml_trainer] epoch #0 | Finished meta-testing... +2025-04-03 17:06:20 | [maml_trainer] epoch #0 | Saving snapshot... +2025-04-03 17:06:38 | [maml_trainer] epoch #0 | Saved +2025-04-03 17:06:38 | [maml_trainer] epoch #0 | Time 1642.92 s +2025-04-03 17:06:38 | [maml_trainer] epoch #0 | EpochTime 1642.92 s +------------------------------------------------- --------------- +Average/AverageDiscountedReturn -82.2053 +Average/AverageReturn -193.763 +Average/Iteration 0 +Average/MaxReturn -134.335 +Average/MinReturn -217.6 +Average/NumEpisodes 120 +Average/StdReturn 18.2797 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92566 +GaussianMLPPolicy/KLAfter 0.0297345 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.1981e-05 +GaussianMLPPolicy/LossBefore -9.63608e-10 +GaussianMLPPolicy/dLoss -8.1982e-05 +Iteration 0 +MetaTest/Average/AverageDiscountedReturn -179.135 +MetaTest/Average/AverageReturn -179.135 +MetaTest/Average/Iteration 0 +MetaTest/Average/MaxReturn -137.176 +MetaTest/Average/MinReturn -216.652 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 24.8925 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -179.135 +MetaTest/__unnamed_task__/AverageReturn -179.135 +MetaTest/__unnamed_task__/Iteration 0 +MetaTest/__unnamed_task__/MaxReturn -137.176 +MetaTest/__unnamed_task__/MinReturn -216.652 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 24.8925 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 48000 +__unnamed_task__/AverageDiscountedReturn -82.2053 +__unnamed_task__/AverageReturn -193.763 +__unnamed_task__/Iteration 0 +__unnamed_task__/MaxReturn -134.335 +__unnamed_task__/MinReturn -217.6 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 18.2797 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- --------------- +2025-04-03 17:29:52 | [maml_trainer] epoch #1 | Sampling for adapation and meta-testing... +2025-04-03 17:33:42 | [maml_trainer] epoch #1 | Finished meta-testing... +2025-04-03 17:33:42 | [maml_trainer] epoch #1 | Saving snapshot... +2025-04-03 17:34:02 | [maml_trainer] epoch #1 | Saved +2025-04-03 17:34:02 | [maml_trainer] epoch #1 | Time 3286.21 s +2025-04-03 17:34:02 | [maml_trainer] epoch #1 | EpochTime 1643.29 s +------------------------------------------------- --------------- +Average/AverageDiscountedReturn -78.4917 +Average/AverageReturn -184.439 +Average/Iteration 1 +Average/MaxReturn -128.929 +Average/MinReturn -221.723 +Average/NumEpisodes 120 +Average/StdReturn 25.6009 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92805 +GaussianMLPPolicy/KLAfter 0.0168477 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.67706e-06 +GaussianMLPPolicy/LossBefore 3.0299e-09 +GaussianMLPPolicy/dLoss 3.68009e-06 +Iteration 1 +MetaTest/Average/AverageDiscountedReturn -183.157 +MetaTest/Average/AverageReturn -183.157 +MetaTest/Average/Iteration 1 +MetaTest/Average/MaxReturn -146.68 +MetaTest/Average/MinReturn -220.859 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 21.4197 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -183.157 +MetaTest/__unnamed_task__/AverageReturn -183.157 +MetaTest/__unnamed_task__/Iteration 1 +MetaTest/__unnamed_task__/MaxReturn -146.68 +MetaTest/__unnamed_task__/MinReturn -220.859 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 21.4197 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 96000 +__unnamed_task__/AverageDiscountedReturn -78.4917 +__unnamed_task__/AverageReturn -184.439 +__unnamed_task__/Iteration 1 +__unnamed_task__/MaxReturn -128.929 +__unnamed_task__/MinReturn -221.723 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 25.6009 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- --------------- +2025-04-03 17:57:10 | [maml_trainer] epoch #2 | Sampling for adapation and meta-testing... +2025-04-03 18:01:01 | [maml_trainer] epoch #2 | Finished meta-testing... +2025-04-03 18:01:01 | [maml_trainer] epoch #2 | Saving snapshot... +2025-04-03 18:01:22 | [maml_trainer] epoch #2 | Saved +2025-04-03 18:01:22 | [maml_trainer] epoch #2 | Time 4926.26 s +2025-04-03 18:01:22 | [maml_trainer] epoch #2 | EpochTime 1640.05 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -73.3937 +Average/AverageReturn -172.945 +Average/Iteration 2 +Average/MaxReturn -126.256 +Average/MinReturn -230.744 +Average/NumEpisodes 120 +Average/StdReturn 26.519 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93248 +GaussianMLPPolicy/KLAfter 0.0111545 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.0001372 +GaussianMLPPolicy/LossBefore -7.2519e-09 +GaussianMLPPolicy/dLoss 0.000137193 +Iteration 2 +MetaTest/Average/AverageDiscountedReturn -159.761 +MetaTest/Average/AverageReturn -159.761 +MetaTest/Average/Iteration 2 +MetaTest/Average/MaxReturn -133.559 +MetaTest/Average/MinReturn -215.737 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 20.5506 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -159.761 +MetaTest/__unnamed_task__/AverageReturn -159.761 +MetaTest/__unnamed_task__/Iteration 2 +MetaTest/__unnamed_task__/MaxReturn -133.559 +MetaTest/__unnamed_task__/MinReturn -215.737 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 20.5506 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 144000 +__unnamed_task__/AverageDiscountedReturn -73.3937 +__unnamed_task__/AverageReturn -172.945 +__unnamed_task__/Iteration 2 +__unnamed_task__/MaxReturn -126.256 +__unnamed_task__/MinReturn -230.744 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.519 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 18:24:39 | [maml_trainer] epoch #3 | Sampling for adapation and meta-testing... +2025-04-03 18:28:31 | [maml_trainer] epoch #3 | Finished meta-testing... +2025-04-03 18:28:31 | [maml_trainer] epoch #3 | Saving snapshot... +2025-04-03 18:28:51 | [maml_trainer] epoch #3 | Saved +2025-04-03 18:28:51 | [maml_trainer] epoch #3 | Time 6575.80 s +2025-04-03 18:28:51 | [maml_trainer] epoch #3 | EpochTime 1649.54 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -70.2883 +Average/AverageReturn -165.004 +Average/Iteration 3 +Average/MaxReturn -131.759 +Average/MinReturn -218.736 +Average/NumEpisodes 120 +Average/StdReturn 22.0294 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93532 +GaussianMLPPolicy/KLAfter 0.00980512 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.78498e-05 +GaussianMLPPolicy/LossBefore 1.15236e-09 +GaussianMLPPolicy/dLoss 7.78509e-05 +Iteration 3 +MetaTest/Average/AverageDiscountedReturn -155.667 +MetaTest/Average/AverageReturn -155.667 +MetaTest/Average/Iteration 3 +MetaTest/Average/MaxReturn -134.895 +MetaTest/Average/MinReturn -207.028 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 19.1626 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -155.667 +MetaTest/__unnamed_task__/AverageReturn -155.667 +MetaTest/__unnamed_task__/Iteration 3 +MetaTest/__unnamed_task__/MaxReturn -134.895 +MetaTest/__unnamed_task__/MinReturn -207.028 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 19.1626 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 192000 +__unnamed_task__/AverageDiscountedReturn -70.2883 +__unnamed_task__/AverageReturn -165.004 +__unnamed_task__/Iteration 3 +__unnamed_task__/MaxReturn -131.759 +__unnamed_task__/MinReturn -218.736 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 22.0294 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 18:52:07 | [maml_trainer] epoch #4 | Sampling for adapation and meta-testing... +2025-04-03 18:56:00 | [maml_trainer] epoch #4 | Finished meta-testing... +2025-04-03 18:56:00 | [maml_trainer] epoch #4 | Saving snapshot... +2025-04-03 18:56:21 | [maml_trainer] epoch #4 | Saved +2025-04-03 18:56:21 | [maml_trainer] epoch #4 | Time 8225.39 s +2025-04-03 18:56:21 | [maml_trainer] epoch #4 | EpochTime 1649.58 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -66.3017 +Average/AverageReturn -155.735 +Average/Iteration 4 +Average/MaxReturn -123.512 +Average/MinReturn -222.567 +Average/NumEpisodes 120 +Average/StdReturn 17.4132 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93762 +GaussianMLPPolicy/KLAfter 0.00974523 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.5226e-05 +GaussianMLPPolicy/LossBefore 6.25849e-09 +GaussianMLPPolicy/dLoss 6.52322e-05 +Iteration 4 +MetaTest/Average/AverageDiscountedReturn -148.552 +MetaTest/Average/AverageReturn -148.552 +MetaTest/Average/Iteration 4 +MetaTest/Average/MaxReturn -133.266 +MetaTest/Average/MinReturn -195.425 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.1364 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -148.552 +MetaTest/__unnamed_task__/AverageReturn -148.552 +MetaTest/__unnamed_task__/Iteration 4 +MetaTest/__unnamed_task__/MaxReturn -133.266 +MetaTest/__unnamed_task__/MinReturn -195.425 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.1364 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 240000 +__unnamed_task__/AverageDiscountedReturn -66.3017 +__unnamed_task__/AverageReturn -155.735 +__unnamed_task__/Iteration 4 +__unnamed_task__/MaxReturn -123.512 +__unnamed_task__/MinReturn -222.567 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.4132 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 19:19:02 | [maml_trainer] epoch #5 | Sampling for adapation and meta-testing... +2025-04-03 19:22:41 | [maml_trainer] epoch #5 | Finished meta-testing... +2025-04-03 19:22:41 | [maml_trainer] epoch #5 | Saving snapshot... +2025-04-03 19:23:00 | [maml_trainer] epoch #5 | Saved +2025-04-03 19:23:00 | [maml_trainer] epoch #5 | Time 9824.86 s +2025-04-03 19:23:00 | [maml_trainer] epoch #5 | EpochTime 1599.47 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -63.4067 +Average/AverageReturn -148.828 +Average/Iteration 5 +Average/MaxReturn -129.488 +Average/MinReturn -186.101 +Average/NumEpisodes 120 +Average/StdReturn 9.23365 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94014 +GaussianMLPPolicy/KLAfter 0.00489618 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.17414e-05 +GaussianMLPPolicy/LossBefore -6.39757e-09 +GaussianMLPPolicy/dLoss 5.1735e-05 +Iteration 5 +MetaTest/Average/AverageDiscountedReturn -144.55 +MetaTest/Average/AverageReturn -144.55 +MetaTest/Average/Iteration 5 +MetaTest/Average/MaxReturn -126.715 +MetaTest/Average/MinReturn -209.422 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.524 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -144.55 +MetaTest/__unnamed_task__/AverageReturn -144.55 +MetaTest/__unnamed_task__/Iteration 5 +MetaTest/__unnamed_task__/MaxReturn -126.715 +MetaTest/__unnamed_task__/MinReturn -209.422 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.524 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 288000 +__unnamed_task__/AverageDiscountedReturn -63.4067 +__unnamed_task__/AverageReturn -148.828 +__unnamed_task__/Iteration 5 +__unnamed_task__/MaxReturn -129.488 +__unnamed_task__/MinReturn -186.101 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.23365 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 19:45:08 | [maml_trainer] epoch #6 | Sampling for adapation and meta-testing... +2025-04-03 19:49:06 | [maml_trainer] epoch #6 | Finished meta-testing... +2025-04-03 19:49:06 | [maml_trainer] epoch #6 | Saving snapshot... +2025-04-03 19:49:26 | [maml_trainer] epoch #6 | Saved +2025-04-03 19:49:26 | [maml_trainer] epoch #6 | Time 11410.93 s +2025-04-03 19:49:26 | [maml_trainer] epoch #6 | EpochTime 1586.06 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -61.965 +Average/AverageReturn -145.442 +Average/Iteration 6 +Average/MaxReturn -125.238 +Average/MinReturn -220.577 +Average/NumEpisodes 120 +Average/StdReturn 12.3678 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94429 +GaussianMLPPolicy/KLAfter 0.00382896 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.01783e-05 +GaussianMLPPolicy/LossBefore 4.43061e-09 +GaussianMLPPolicy/dLoss -4.01738e-05 +Iteration 6 +MetaTest/Average/AverageDiscountedReturn -145.659 +MetaTest/Average/AverageReturn -145.659 +MetaTest/Average/Iteration 6 +MetaTest/Average/MaxReturn -132.179 +MetaTest/Average/MinReturn -169.705 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.14661 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -145.659 +MetaTest/__unnamed_task__/AverageReturn -145.659 +MetaTest/__unnamed_task__/Iteration 6 +MetaTest/__unnamed_task__/MaxReturn -132.179 +MetaTest/__unnamed_task__/MinReturn -169.705 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.14661 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 336000 +__unnamed_task__/AverageDiscountedReturn -61.965 +__unnamed_task__/AverageReturn -145.442 +__unnamed_task__/Iteration 6 +__unnamed_task__/MaxReturn -125.238 +__unnamed_task__/MinReturn -220.577 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.3678 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 20:13:20 | [maml_trainer] epoch #7 | Sampling for adapation and meta-testing... +2025-04-03 20:17:03 | [maml_trainer] epoch #7 | Finished meta-testing... +2025-04-03 20:17:03 | [maml_trainer] epoch #7 | Saving snapshot... +2025-04-03 20:17:23 | [maml_trainer] epoch #7 | Saved +2025-04-03 20:17:23 | [maml_trainer] epoch #7 | Time 13087.38 s +2025-04-03 20:17:23 | [maml_trainer] epoch #7 | EpochTime 1676.45 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -61.8576 +Average/AverageReturn -144.795 +Average/Iteration 7 +Average/MaxReturn -122.64 +Average/MinReturn -206.512 +Average/NumEpisodes 120 +Average/StdReturn 11.5804 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94718 +GaussianMLPPolicy/KLAfter 0.00578938 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.91971e-06 +GaussianMLPPolicy/LossBefore -1.20004e-08 +GaussianMLPPolicy/dLoss 4.90771e-06 +Iteration 7 +MetaTest/Average/AverageDiscountedReturn -144.293 +MetaTest/Average/AverageReturn -144.293 +MetaTest/Average/Iteration 7 +MetaTest/Average/MaxReturn -130.101 +MetaTest/Average/MinReturn -156.358 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.62275 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -144.293 +MetaTest/__unnamed_task__/AverageReturn -144.293 +MetaTest/__unnamed_task__/Iteration 7 +MetaTest/__unnamed_task__/MaxReturn -130.101 +MetaTest/__unnamed_task__/MinReturn -156.358 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.62275 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 384000 +__unnamed_task__/AverageDiscountedReturn -61.8576 +__unnamed_task__/AverageReturn -144.795 +__unnamed_task__/Iteration 7 +__unnamed_task__/MaxReturn -122.64 +__unnamed_task__/MinReturn -206.512 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.5804 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 20:40:26 | [maml_trainer] epoch #8 | Sampling for adapation and meta-testing... +2025-04-03 20:44:18 | [maml_trainer] epoch #8 | Finished meta-testing... +2025-04-03 20:44:18 | [maml_trainer] epoch #8 | Saving snapshot... +2025-04-03 20:44:39 | [maml_trainer] epoch #8 | Saved +2025-04-03 20:44:39 | [maml_trainer] epoch #8 | Time 14723.39 s +2025-04-03 20:44:39 | [maml_trainer] epoch #8 | EpochTime 1636.00 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -60.2078 +Average/AverageReturn -140.792 +Average/Iteration 8 +Average/MaxReturn -123.458 +Average/MinReturn -159.832 +Average/NumEpisodes 120 +Average/StdReturn 8.11926 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94711 +GaussianMLPPolicy/KLAfter 0.00472086 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000102256 +GaussianMLPPolicy/LossBefore 2.16564e-09 +GaussianMLPPolicy/dLoss 0.000102258 +Iteration 8 +MetaTest/Average/AverageDiscountedReturn -138.268 +MetaTest/Average/AverageReturn -138.268 +MetaTest/Average/Iteration 8 +MetaTest/Average/MaxReturn -130.562 +MetaTest/Average/MinReturn -159.357 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.40614 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -138.268 +MetaTest/__unnamed_task__/AverageReturn -138.268 +MetaTest/__unnamed_task__/Iteration 8 +MetaTest/__unnamed_task__/MaxReturn -130.562 +MetaTest/__unnamed_task__/MinReturn -159.357 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.40614 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 432000 +__unnamed_task__/AverageDiscountedReturn -60.2078 +__unnamed_task__/AverageReturn -140.792 +__unnamed_task__/Iteration 8 +__unnamed_task__/MaxReturn -123.458 +__unnamed_task__/MinReturn -159.832 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.11926 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 21:07:38 | [maml_trainer] epoch #9 | Sampling for adapation and meta-testing... +2025-04-03 21:11:35 | [maml_trainer] epoch #9 | Finished meta-testing... +2025-04-03 21:11:35 | [maml_trainer] epoch #9 | Saving snapshot... +2025-04-03 21:11:54 | [maml_trainer] epoch #9 | Saved +2025-04-03 21:11:54 | [maml_trainer] epoch #9 | Time 16358.88 s +2025-04-03 21:11:54 | [maml_trainer] epoch #9 | EpochTime 1635.49 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -59.3589 +Average/AverageReturn -138.663 +Average/Iteration 9 +Average/MaxReturn -122.16 +Average/MinReturn -168.294 +Average/NumEpisodes 120 +Average/StdReturn 8.32631 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94788 +GaussianMLPPolicy/KLAfter 0.00520743 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.14686e-06 +GaussianMLPPolicy/LossBefore 5.64257e-09 +GaussianMLPPolicy/dLoss 5.1525e-06 +Iteration 9 +MetaTest/Average/AverageDiscountedReturn -136.915 +MetaTest/Average/AverageReturn -136.915 +MetaTest/Average/Iteration 9 +MetaTest/Average/MaxReturn -122.67 +MetaTest/Average/MinReturn -156.111 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.23241 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -136.915 +MetaTest/__unnamed_task__/AverageReturn -136.915 +MetaTest/__unnamed_task__/Iteration 9 +MetaTest/__unnamed_task__/MaxReturn -122.67 +MetaTest/__unnamed_task__/MinReturn -156.111 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.23241 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 480000 +__unnamed_task__/AverageDiscountedReturn -59.3589 +__unnamed_task__/AverageReturn -138.663 +__unnamed_task__/Iteration 9 +__unnamed_task__/MaxReturn -122.16 +__unnamed_task__/MinReturn -168.294 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.32631 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 21:34:58 | [maml_trainer] epoch #10 | Sampling for adapation and meta-testing... +2025-04-03 21:38:36 | [maml_trainer] epoch #10 | Finished meta-testing... +2025-04-03 21:38:36 | [maml_trainer] epoch #10 | Saving snapshot... +2025-04-03 21:38:55 | [maml_trainer] epoch #10 | Saved +2025-04-03 21:38:55 | [maml_trainer] epoch #10 | Time 17979.21 s +2025-04-03 21:38:55 | [maml_trainer] epoch #10 | EpochTime 1620.33 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -59.5652 +Average/AverageReturn -139.267 +Average/Iteration 10 +Average/MaxReturn -116.88 +Average/MinReturn -160.964 +Average/NumEpisodes 120 +Average/StdReturn 8.29386 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94782 +GaussianMLPPolicy/KLAfter 0.00495302 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000104325 +GaussianMLPPolicy/LossBefore 1.6888e-09 +GaussianMLPPolicy/dLoss 0.000104327 +Iteration 10 +MetaTest/Average/AverageDiscountedReturn -135.115 +MetaTest/Average/AverageReturn -135.115 +MetaTest/Average/Iteration 10 +MetaTest/Average/MaxReturn -125.062 +MetaTest/Average/MinReturn -146.583 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.29427 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -135.115 +MetaTest/__unnamed_task__/AverageReturn -135.115 +MetaTest/__unnamed_task__/Iteration 10 +MetaTest/__unnamed_task__/MaxReturn -125.062 +MetaTest/__unnamed_task__/MinReturn -146.583 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.29427 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 528000 +__unnamed_task__/AverageDiscountedReturn -59.5652 +__unnamed_task__/AverageReturn -139.267 +__unnamed_task__/Iteration 10 +__unnamed_task__/MaxReturn -116.88 +__unnamed_task__/MinReturn -160.964 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.29386 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 22:00:41 | [maml_trainer] epoch #11 | Sampling for adapation and meta-testing... +2025-04-03 22:04:16 | [maml_trainer] epoch #11 | Finished meta-testing... +2025-04-03 22:04:16 | [maml_trainer] epoch #11 | Saving snapshot... +2025-04-03 22:04:35 | [maml_trainer] epoch #11 | Saved +2025-04-03 22:04:35 | [maml_trainer] epoch #11 | Time 19519.04 s +2025-04-03 22:04:35 | [maml_trainer] epoch #11 | EpochTime 1539.82 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -58.8037 +Average/AverageReturn -136.933 +Average/Iteration 11 +Average/MaxReturn -123.062 +Average/MinReturn -154.384 +Average/NumEpisodes 120 +Average/StdReturn 6.91497 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94898 +GaussianMLPPolicy/KLAfter 0.00643462 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.26917e-05 +GaussianMLPPolicy/LossBefore 5.98033e-09 +GaussianMLPPolicy/dLoss 3.26977e-05 +Iteration 11 +MetaTest/Average/AverageDiscountedReturn -137.298 +MetaTest/Average/AverageReturn -137.298 +MetaTest/Average/Iteration 11 +MetaTest/Average/MaxReturn -123.181 +MetaTest/Average/MinReturn -151.064 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.15146 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -137.298 +MetaTest/__unnamed_task__/AverageReturn -137.298 +MetaTest/__unnamed_task__/Iteration 11 +MetaTest/__unnamed_task__/MaxReturn -123.181 +MetaTest/__unnamed_task__/MinReturn -151.064 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.15146 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 576000 +__unnamed_task__/AverageDiscountedReturn -58.8037 +__unnamed_task__/AverageReturn -136.933 +__unnamed_task__/Iteration 11 +__unnamed_task__/MaxReturn -123.062 +__unnamed_task__/MinReturn -154.384 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.91497 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 22:27:43 | [maml_trainer] epoch #12 | Sampling for adapation and meta-testing... +2025-04-03 22:31:49 | [maml_trainer] epoch #12 | Finished meta-testing... +2025-04-03 22:31:49 | [maml_trainer] epoch #12 | Saving snapshot... +2025-04-03 22:32:10 | [maml_trainer] epoch #12 | Saved +2025-04-03 22:32:10 | [maml_trainer] epoch #12 | Time 21174.19 s +2025-04-03 22:32:10 | [maml_trainer] epoch #12 | EpochTime 1655.15 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -58.7409 +Average/AverageReturn -136.808 +Average/Iteration 12 +Average/MaxReturn -118.86 +Average/MinReturn -160.008 +Average/NumEpisodes 120 +Average/StdReturn 7.67521 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95082 +GaussianMLPPolicy/KLAfter 0.00604509 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.11096e-05 +GaussianMLPPolicy/LossBefore 7.17243e-09 +GaussianMLPPolicy/dLoss 3.11167e-05 +Iteration 12 +MetaTest/Average/AverageDiscountedReturn -128.304 +MetaTest/Average/AverageReturn -128.304 +MetaTest/Average/Iteration 12 +MetaTest/Average/MaxReturn -117.034 +MetaTest/Average/MinReturn -154.988 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.77891 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -128.304 +MetaTest/__unnamed_task__/AverageReturn -128.304 +MetaTest/__unnamed_task__/Iteration 12 +MetaTest/__unnamed_task__/MaxReturn -117.034 +MetaTest/__unnamed_task__/MinReturn -154.988 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.77891 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 624000 +__unnamed_task__/AverageDiscountedReturn -58.7409 +__unnamed_task__/AverageReturn -136.808 +__unnamed_task__/Iteration 12 +__unnamed_task__/MaxReturn -118.86 +__unnamed_task__/MinReturn -160.008 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.67521 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 22:54:49 | [maml_trainer] epoch #13 | Sampling for adapation and meta-testing... +2025-04-03 22:58:46 | [maml_trainer] epoch #13 | Finished meta-testing... +2025-04-03 22:58:46 | [maml_trainer] epoch #13 | Saving snapshot... +2025-04-03 22:59:06 | [maml_trainer] epoch #13 | Saved +2025-04-03 22:59:06 | [maml_trainer] epoch #13 | Time 22790.72 s +2025-04-03 22:59:06 | [maml_trainer] epoch #13 | EpochTime 1616.53 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -57.2712 +Average/AverageReturn -132.688 +Average/Iteration 13 +Average/MaxReturn -110.178 +Average/MinReturn -153.897 +Average/NumEpisodes 120 +Average/StdReturn 8.37591 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95336 +GaussianMLPPolicy/KLAfter 0.00391486 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.95175e-05 +GaussianMLPPolicy/LossBefore 4.37101e-10 +GaussianMLPPolicy/dLoss 4.95179e-05 +Iteration 13 +MetaTest/Average/AverageDiscountedReturn -131.901 +MetaTest/Average/AverageReturn -131.901 +MetaTest/Average/Iteration 13 +MetaTest/Average/MaxReturn -118.047 +MetaTest/Average/MinReturn -150.287 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.05101 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -131.901 +MetaTest/__unnamed_task__/AverageReturn -131.901 +MetaTest/__unnamed_task__/Iteration 13 +MetaTest/__unnamed_task__/MaxReturn -118.047 +MetaTest/__unnamed_task__/MinReturn -150.287 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.05101 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 672000 +__unnamed_task__/AverageDiscountedReturn -57.2712 +__unnamed_task__/AverageReturn -132.688 +__unnamed_task__/Iteration 13 +__unnamed_task__/MaxReturn -110.178 +__unnamed_task__/MinReturn -153.897 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.37591 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 23:22:25 | [maml_trainer] epoch #14 | Sampling for adapation and meta-testing... +2025-04-03 23:26:19 | [maml_trainer] epoch #14 | Finished meta-testing... +2025-04-03 23:26:19 | [maml_trainer] epoch #14 | Saving snapshot... +2025-04-03 23:26:40 | [maml_trainer] epoch #14 | Saved +2025-04-03 23:26:40 | [maml_trainer] epoch #14 | Time 24444.45 s +2025-04-03 23:26:40 | [maml_trainer] epoch #14 | EpochTime 1653.72 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -56.2572 +Average/AverageReturn -129.545 +Average/Iteration 14 +Average/MaxReturn -112.896 +Average/MinReturn -149.027 +Average/NumEpisodes 120 +Average/StdReturn 7.53097 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95491 +GaussianMLPPolicy/KLAfter 0.0057979 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.56015e-05 +GaussianMLPPolicy/LossBefore 5.86112e-09 +GaussianMLPPolicy/dLoss 7.56073e-05 +Iteration 14 +MetaTest/Average/AverageDiscountedReturn -131.692 +MetaTest/Average/AverageReturn -131.692 +MetaTest/Average/Iteration 14 +MetaTest/Average/MaxReturn -118.392 +MetaTest/Average/MinReturn -148.562 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.77233 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -131.692 +MetaTest/__unnamed_task__/AverageReturn -131.692 +MetaTest/__unnamed_task__/Iteration 14 +MetaTest/__unnamed_task__/MaxReturn -118.392 +MetaTest/__unnamed_task__/MinReturn -148.562 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.77233 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 720000 +__unnamed_task__/AverageDiscountedReturn -56.2572 +__unnamed_task__/AverageReturn -129.545 +__unnamed_task__/Iteration 14 +__unnamed_task__/MaxReturn -112.896 +__unnamed_task__/MinReturn -149.027 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.53097 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-03 23:50:32 | [maml_trainer] epoch #15 | Sampling for adapation and meta-testing... +2025-04-03 23:54:29 | [maml_trainer] epoch #15 | Finished meta-testing... +2025-04-03 23:54:29 | [maml_trainer] epoch #15 | Saving snapshot... +2025-04-03 23:54:49 | [maml_trainer] epoch #15 | Saved +2025-04-03 23:54:49 | [maml_trainer] epoch #15 | Time 26133.78 s +2025-04-03 23:54:49 | [maml_trainer] epoch #15 | EpochTime 1689.32 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -56.5967 +Average/AverageReturn -130.133 +Average/Iteration 15 +Average/MaxReturn -112.862 +Average/MinReturn -146.542 +Average/NumEpisodes 120 +Average/StdReturn 7.637 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95664 +GaussianMLPPolicy/KLAfter 0.00825869 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.98916e-05 +GaussianMLPPolicy/LossBefore 1.15236e-08 +GaussianMLPPolicy/dLoss 5.99031e-05 +Iteration 15 +MetaTest/Average/AverageDiscountedReturn -126.612 +MetaTest/Average/AverageReturn -126.612 +MetaTest/Average/Iteration 15 +MetaTest/Average/MaxReturn -116.913 +MetaTest/Average/MinReturn -137.11 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.37274 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -126.612 +MetaTest/__unnamed_task__/AverageReturn -126.612 +MetaTest/__unnamed_task__/Iteration 15 +MetaTest/__unnamed_task__/MaxReturn -116.913 +MetaTest/__unnamed_task__/MinReturn -137.11 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.37274 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 768000 +__unnamed_task__/AverageDiscountedReturn -56.5967 +__unnamed_task__/AverageReturn -130.133 +__unnamed_task__/Iteration 15 +__unnamed_task__/MaxReturn -112.862 +__unnamed_task__/MinReturn -146.542 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.637 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-04 00:18:22 | [maml_trainer] epoch #16 | Sampling for adapation and meta-testing... +2025-04-04 00:22:18 | [maml_trainer] epoch #16 | Finished meta-testing... +2025-04-04 00:22:18 | [maml_trainer] epoch #16 | Saving snapshot... +2025-04-04 00:22:39 | [maml_trainer] epoch #16 | Saved +2025-04-04 00:22:39 | [maml_trainer] epoch #16 | Time 27803.28 s +2025-04-04 00:22:39 | [maml_trainer] epoch #16 | EpochTime 1669.50 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -55.1648 +Average/AverageReturn -125.952 +Average/Iteration 16 +Average/MaxReturn -105.804 +Average/MinReturn -143.543 +Average/NumEpisodes 120 +Average/StdReturn 8.06455 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95812 +GaussianMLPPolicy/KLAfter 0.011384 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.5789e-06 +GaussianMLPPolicy/LossBefore -5.28495e-09 +GaussianMLPPolicy/dLoss 9.57362e-06 +Iteration 16 +MetaTest/Average/AverageDiscountedReturn -124.015 +MetaTest/Average/AverageReturn -124.015 +MetaTest/Average/Iteration 16 +MetaTest/Average/MaxReturn -116.438 +MetaTest/Average/MinReturn -143.03 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.23648 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -124.015 +MetaTest/__unnamed_task__/AverageReturn -124.015 +MetaTest/__unnamed_task__/Iteration 16 +MetaTest/__unnamed_task__/MaxReturn -116.438 +MetaTest/__unnamed_task__/MinReturn -143.03 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.23648 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 816000 +__unnamed_task__/AverageDiscountedReturn -55.1648 +__unnamed_task__/AverageReturn -125.952 +__unnamed_task__/Iteration 16 +__unnamed_task__/MaxReturn -105.804 +__unnamed_task__/MinReturn -143.543 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.06455 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-04 00:46:15 | [maml_trainer] epoch #17 | Sampling for adapation and meta-testing... +2025-04-04 00:50:13 | [maml_trainer] epoch #17 | Finished meta-testing... +2025-04-04 00:50:13 | [maml_trainer] epoch #17 | Saving snapshot... +2025-04-04 00:50:33 | [maml_trainer] epoch #17 | Saved +2025-04-04 00:50:33 | [maml_trainer] epoch #17 | Time 29477.62 s +2025-04-04 00:50:33 | [maml_trainer] epoch #17 | EpochTime 1674.34 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -54.7048 +Average/AverageReturn -124.192 +Average/Iteration 17 +Average/MaxReturn -102.592 +Average/MinReturn -147.264 +Average/NumEpisodes 120 +Average/StdReturn 9.56627 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96001 +GaussianMLPPolicy/KLAfter 0.0113182 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.70992e-05 +GaussianMLPPolicy/LossBefore -8.72215e-09 +GaussianMLPPolicy/dLoss 4.70905e-05 +Iteration 17 +MetaTest/Average/AverageDiscountedReturn -118.769 +MetaTest/Average/AverageReturn -118.769 +MetaTest/Average/Iteration 17 +MetaTest/Average/MaxReturn -105.953 +MetaTest/Average/MinReturn -137.455 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.61785 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -118.769 +MetaTest/__unnamed_task__/AverageReturn -118.769 +MetaTest/__unnamed_task__/Iteration 17 +MetaTest/__unnamed_task__/MaxReturn -105.953 +MetaTest/__unnamed_task__/MinReturn -137.455 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.61785 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 864000 +__unnamed_task__/AverageDiscountedReturn -54.7048 +__unnamed_task__/AverageReturn -124.192 +__unnamed_task__/Iteration 17 +__unnamed_task__/MaxReturn -102.592 +__unnamed_task__/MinReturn -147.264 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.56627 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-04 01:14:12 | [maml_trainer] epoch #18 | Sampling for adapation and meta-testing... +2025-04-04 01:18:07 | [maml_trainer] epoch #18 | Finished meta-testing... +2025-04-04 01:18:07 | [maml_trainer] epoch #18 | Saving snapshot... +2025-04-04 01:18:28 | [maml_trainer] epoch #18 | Saved +2025-04-04 01:18:28 | [maml_trainer] epoch #18 | Time 31152.13 s +2025-04-04 01:18:28 | [maml_trainer] epoch #18 | EpochTime 1674.50 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -53.4122 +Average/AverageReturn -120.279 +Average/Iteration 18 +Average/MaxReturn -100.466 +Average/MinReturn -145.292 +Average/NumEpisodes 120 +Average/StdReturn 8.5785 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95999 +GaussianMLPPolicy/KLAfter 0.0129157 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.02627e-05 +GaussianMLPPolicy/LossBefore 4.39088e-09 +GaussianMLPPolicy/dLoss 5.02671e-05 +Iteration 18 +MetaTest/Average/AverageDiscountedReturn -116.231 +MetaTest/Average/AverageReturn -116.231 +MetaTest/Average/Iteration 18 +MetaTest/Average/MaxReturn -106.749 +MetaTest/Average/MinReturn -128.354 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.88189 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -116.231 +MetaTest/__unnamed_task__/AverageReturn -116.231 +MetaTest/__unnamed_task__/Iteration 18 +MetaTest/__unnamed_task__/MaxReturn -106.749 +MetaTest/__unnamed_task__/MinReturn -128.354 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.88189 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 912000 +__unnamed_task__/AverageDiscountedReturn -53.4122 +__unnamed_task__/AverageReturn -120.279 +__unnamed_task__/Iteration 18 +__unnamed_task__/MaxReturn -100.466 +__unnamed_task__/MinReturn -145.292 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.5785 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-04 01:40:39 | [maml_trainer] epoch #19 | Sampling for adapation and meta-testing... +2025-04-04 01:44:23 | [maml_trainer] epoch #19 | Finished meta-testing... +2025-04-04 01:44:23 | [maml_trainer] epoch #19 | Saving snapshot... +2025-04-04 01:44:43 | [maml_trainer] epoch #19 | Saved +2025-04-04 01:44:43 | [maml_trainer] epoch #19 | Time 32727.24 s +2025-04-04 01:44:43 | [maml_trainer] epoch #19 | EpochTime 1575.11 s +------------------------------------------------- ---------------- +Average/AverageDiscountedReturn -51.3934 +Average/AverageReturn -114.451 +Average/Iteration 19 +Average/MaxReturn -96.3453 +Average/MinReturn -137.922 +Average/NumEpisodes 120 +Average/StdReturn 8.79287 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96059 +GaussianMLPPolicy/KLAfter 0.0120949 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.37757e-06 +GaussianMLPPolicy/LossBefore 1.47025e-09 +GaussianMLPPolicy/dLoss 5.37904e-06 +Iteration 19 +MetaTest/Average/AverageDiscountedReturn -112.474 +MetaTest/Average/AverageReturn -112.474 +MetaTest/Average/Iteration 19 +MetaTest/Average/MaxReturn -101.272 +MetaTest/Average/MinReturn -133.748 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.9087 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -112.474 +MetaTest/__unnamed_task__/AverageReturn -112.474 +MetaTest/__unnamed_task__/Iteration 19 +MetaTest/__unnamed_task__/MaxReturn -101.272 +MetaTest/__unnamed_task__/MinReturn -133.748 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.9087 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 960000 +__unnamed_task__/AverageDiscountedReturn -51.3934 +__unnamed_task__/AverageReturn -114.451 +__unnamed_task__/Iteration 19 +__unnamed_task__/MaxReturn -96.3453 +__unnamed_task__/MinReturn -137.922 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.79287 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ---------------- +2025-04-04 02:06:55 | [maml_trainer] epoch #20 | Sampling for adapation and meta-testing... +2025-04-04 02:10:36 | [maml_trainer] epoch #20 | Finished meta-testing... +2025-04-04 02:10:36 | [maml_trainer] epoch #20 | Saving snapshot... +2025-04-04 02:10:56 | [maml_trainer] epoch #20 | Saved +2025-04-04 02:10:56 | [maml_trainer] epoch #20 | Time 34300.06 s +2025-04-04 02:10:56 | [maml_trainer] epoch #20 | EpochTime 1572.81 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -50.0141 +Average/AverageReturn -110.339 +Average/Iteration 20 +Average/MaxReturn -91.891 +Average/MinReturn -133.976 +Average/NumEpisodes 120 +Average/StdReturn 7.75056 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96143 +GaussianMLPPolicy/KLAfter 0.00985724 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.86122e-06 +GaussianMLPPolicy/LossBefore 1.16825e-08 +GaussianMLPPolicy/dLoss 2.8729e-06 +Iteration 20 +MetaTest/Average/AverageDiscountedReturn -107.424 +MetaTest/Average/AverageReturn -107.424 +MetaTest/Average/Iteration 20 +MetaTest/Average/MaxReturn -93.3441 +MetaTest/Average/MinReturn -124.559 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.45655 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -107.424 +MetaTest/__unnamed_task__/AverageReturn -107.424 +MetaTest/__unnamed_task__/Iteration 20 +MetaTest/__unnamed_task__/MaxReturn -93.3441 +MetaTest/__unnamed_task__/MinReturn -124.559 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.45655 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.008e+06 +__unnamed_task__/AverageDiscountedReturn -50.0141 +__unnamed_task__/AverageReturn -110.339 +__unnamed_task__/Iteration 20 +__unnamed_task__/MaxReturn -91.891 +__unnamed_task__/MinReturn -133.976 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.75056 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 02:33:06 | [maml_trainer] epoch #21 | Sampling for adapation and meta-testing... +2025-04-04 02:36:47 | [maml_trainer] epoch #21 | Finished meta-testing... +2025-04-04 02:36:47 | [maml_trainer] epoch #21 | Saving snapshot... +2025-04-04 02:37:06 | [maml_trainer] epoch #21 | Saved +2025-04-04 02:37:06 | [maml_trainer] epoch #21 | Time 35870.69 s +2025-04-04 02:37:06 | [maml_trainer] epoch #21 | EpochTime 1570.63 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -49.3972 +Average/AverageReturn -107.91 +Average/Iteration 21 +Average/MaxReturn -89.7106 +Average/MinReturn -130.812 +Average/NumEpisodes 120 +Average/StdReturn 8.06753 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96162 +GaussianMLPPolicy/KLAfter 0.00856512 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.11969e-05 +GaussianMLPPolicy/LossBefore -2.28484e-09 +GaussianMLPPolicy/dLoss 9.11947e-05 +Iteration 21 +MetaTest/Average/AverageDiscountedReturn -101.914 +MetaTest/Average/AverageReturn -101.914 +MetaTest/Average/Iteration 21 +MetaTest/Average/MaxReturn -88.898 +MetaTest/Average/MinReturn -115.002 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.0148 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -101.914 +MetaTest/__unnamed_task__/AverageReturn -101.914 +MetaTest/__unnamed_task__/Iteration 21 +MetaTest/__unnamed_task__/MaxReturn -88.898 +MetaTest/__unnamed_task__/MinReturn -115.002 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.0148 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.056e+06 +__unnamed_task__/AverageDiscountedReturn -49.3972 +__unnamed_task__/AverageReturn -107.91 +__unnamed_task__/Iteration 21 +__unnamed_task__/MaxReturn -89.7106 +__unnamed_task__/MinReturn -130.812 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.06753 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 02:58:50 | [maml_trainer] epoch #22 | Sampling for adapation and meta-testing... +2025-04-04 03:02:30 | [maml_trainer] epoch #22 | Finished meta-testing... +2025-04-04 03:02:30 | [maml_trainer] epoch #22 | Saving snapshot... +2025-04-04 03:02:49 | [maml_trainer] epoch #22 | Saved +2025-04-04 03:02:49 | [maml_trainer] epoch #22 | Time 37413.40 s +2025-04-04 03:02:49 | [maml_trainer] epoch #22 | EpochTime 1542.71 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -48.0902 +Average/AverageReturn -104.152 +Average/Iteration 22 +Average/MaxReturn -80.4207 +Average/MinReturn -125.246 +Average/NumEpisodes 120 +Average/StdReturn 8.5268 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96169 +GaussianMLPPolicy/KLAfter 0.00901658 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.62834e-07 +GaussianMLPPolicy/LossBefore -1.29938e-08 +GaussianMLPPolicy/dLoss -3.75828e-07 +Iteration 22 +MetaTest/Average/AverageDiscountedReturn -103.354 +MetaTest/Average/AverageReturn -103.354 +MetaTest/Average/Iteration 22 +MetaTest/Average/MaxReturn -92.2119 +MetaTest/Average/MinReturn -115.833 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.73109 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -103.354 +MetaTest/__unnamed_task__/AverageReturn -103.354 +MetaTest/__unnamed_task__/Iteration 22 +MetaTest/__unnamed_task__/MaxReturn -92.2119 +MetaTest/__unnamed_task__/MinReturn -115.833 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.73109 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.104e+06 +__unnamed_task__/AverageDiscountedReturn -48.0902 +__unnamed_task__/AverageReturn -104.152 +__unnamed_task__/Iteration 22 +__unnamed_task__/MaxReturn -80.4207 +__unnamed_task__/MinReturn -125.246 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.5268 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 03:24:48 | [maml_trainer] epoch #23 | Sampling for adapation and meta-testing... +2025-04-04 03:28:29 | [maml_trainer] epoch #23 | Finished meta-testing... +2025-04-04 03:28:29 | [maml_trainer] epoch #23 | Saving snapshot... +2025-04-04 03:28:48 | [maml_trainer] epoch #23 | Saved +2025-04-04 03:28:48 | [maml_trainer] epoch #23 | Time 38972.25 s +2025-04-04 03:28:48 | [maml_trainer] epoch #23 | EpochTime 1558.85 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -47.6611 +Average/AverageReturn -102.507 +Average/Iteration 23 +Average/MaxReturn -86.4267 +Average/MinReturn -125.076 +Average/NumEpisodes 120 +Average/StdReturn 8.14207 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96063 +GaussianMLPPolicy/KLAfter 0.00978113 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.88531e-05 +GaussianMLPPolicy/LossBefore 3.69549e-09 +GaussianMLPPolicy/dLoss 9.88568e-05 +Iteration 23 +MetaTest/Average/AverageDiscountedReturn -99.5005 +MetaTest/Average/AverageReturn -99.5005 +MetaTest/Average/Iteration 23 +MetaTest/Average/MaxReturn -85.3564 +MetaTest/Average/MinReturn -120.559 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.94608 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -99.5005 +MetaTest/__unnamed_task__/AverageReturn -99.5005 +MetaTest/__unnamed_task__/Iteration 23 +MetaTest/__unnamed_task__/MaxReturn -85.3564 +MetaTest/__unnamed_task__/MinReturn -120.559 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.94608 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.152e+06 +__unnamed_task__/AverageDiscountedReturn -47.6611 +__unnamed_task__/AverageReturn -102.507 +__unnamed_task__/Iteration 23 +__unnamed_task__/MaxReturn -86.4267 +__unnamed_task__/MinReturn -125.076 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.14207 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 03:50:27 | [maml_trainer] epoch #24 | Sampling for adapation and meta-testing... +2025-04-04 03:54:06 | [maml_trainer] epoch #24 | Finished meta-testing... +2025-04-04 03:54:06 | [maml_trainer] epoch #24 | Saving snapshot... +2025-04-04 03:54:25 | [maml_trainer] epoch #24 | Saved +2025-04-04 03:54:25 | [maml_trainer] epoch #24 | Time 40509.37 s +2025-04-04 03:54:25 | [maml_trainer] epoch #24 | EpochTime 1537.12 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -46.3213 +Average/AverageReturn -98.9785 +Average/Iteration 24 +Average/MaxReturn -75 +Average/MinReturn -123.25 +Average/NumEpisodes 120 +Average/StdReturn 8.16332 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95844 +GaussianMLPPolicy/KLAfter 0.00689651 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.58248e-05 +GaussianMLPPolicy/LossBefore -4.76837e-09 +GaussianMLPPolicy/dLoss 6.582e-05 +Iteration 24 +MetaTest/Average/AverageDiscountedReturn -97.6783 +MetaTest/Average/AverageReturn -97.6783 +MetaTest/Average/Iteration 24 +MetaTest/Average/MaxReturn -83.1939 +MetaTest/Average/MinReturn -113.379 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.24557 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -97.6783 +MetaTest/__unnamed_task__/AverageReturn -97.6783 +MetaTest/__unnamed_task__/Iteration 24 +MetaTest/__unnamed_task__/MaxReturn -83.1939 +MetaTest/__unnamed_task__/MinReturn -113.379 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.24557 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2e+06 +__unnamed_task__/AverageDiscountedReturn -46.3213 +__unnamed_task__/AverageReturn -98.9785 +__unnamed_task__/Iteration 24 +__unnamed_task__/MaxReturn -75 +__unnamed_task__/MinReturn -123.25 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.16332 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 04:16:18 | [maml_trainer] epoch #25 | Sampling for adapation and meta-testing... +2025-04-04 04:19:57 | [maml_trainer] epoch #25 | Finished meta-testing... +2025-04-04 04:19:57 | [maml_trainer] epoch #25 | Saving snapshot... +2025-04-04 04:20:17 | [maml_trainer] epoch #25 | Saved +2025-04-04 04:20:17 | [maml_trainer] epoch #25 | Time 42061.66 s +2025-04-04 04:20:17 | [maml_trainer] epoch #25 | EpochTime 1552.29 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -45.6381 +Average/AverageReturn -97.0585 +Average/Iteration 25 +Average/MaxReturn -81.381 +Average/MinReturn -117.359 +Average/NumEpisodes 120 +Average/StdReturn 7.45153 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95759 +GaussianMLPPolicy/KLAfter 0.00591015 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.26537e-05 +GaussianMLPPolicy/LossBefore 1.19209e-10 +GaussianMLPPolicy/dLoss 7.26538e-05 +Iteration 25 +MetaTest/Average/AverageDiscountedReturn -94.4554 +MetaTest/Average/AverageReturn -94.4554 +MetaTest/Average/Iteration 25 +MetaTest/Average/MaxReturn -79.8159 +MetaTest/Average/MinReturn -111.48 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.54998 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -94.4554 +MetaTest/__unnamed_task__/AverageReturn -94.4554 +MetaTest/__unnamed_task__/Iteration 25 +MetaTest/__unnamed_task__/MaxReturn -79.8159 +MetaTest/__unnamed_task__/MinReturn -111.48 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.54998 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.248e+06 +__unnamed_task__/AverageDiscountedReturn -45.6381 +__unnamed_task__/AverageReturn -97.0585 +__unnamed_task__/Iteration 25 +__unnamed_task__/MaxReturn -81.381 +__unnamed_task__/MinReturn -117.359 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.45153 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 04:42:11 | [maml_trainer] epoch #26 | Sampling for adapation and meta-testing... +2025-04-04 04:45:52 | [maml_trainer] epoch #26 | Finished meta-testing... +2025-04-04 04:45:52 | [maml_trainer] epoch #26 | Saving snapshot... +2025-04-04 04:46:11 | [maml_trainer] epoch #26 | Saved +2025-04-04 04:46:11 | [maml_trainer] epoch #26 | Time 43615.76 s +2025-04-04 04:46:11 | [maml_trainer] epoch #26 | EpochTime 1554.09 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -44.2009 +Average/AverageReturn -93.2869 +Average/Iteration 26 +Average/MaxReturn -76.9273 +Average/MinReturn -110.985 +Average/NumEpisodes 120 +Average/StdReturn 7.73727 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95664 +GaussianMLPPolicy/KLAfter 0.00882355 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.1777e-05 +GaussianMLPPolicy/LossBefore 4.80811e-09 +GaussianMLPPolicy/dLoss 9.17818e-05 +Iteration 26 +MetaTest/Average/AverageDiscountedReturn -92.4372 +MetaTest/Average/AverageReturn -92.4372 +MetaTest/Average/Iteration 26 +MetaTest/Average/MaxReturn -77.5005 +MetaTest/Average/MinReturn -104.185 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.55209 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -92.4372 +MetaTest/__unnamed_task__/AverageReturn -92.4372 +MetaTest/__unnamed_task__/Iteration 26 +MetaTest/__unnamed_task__/MaxReturn -77.5005 +MetaTest/__unnamed_task__/MinReturn -104.185 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.55209 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.296e+06 +__unnamed_task__/AverageDiscountedReturn -44.2009 +__unnamed_task__/AverageReturn -93.2869 +__unnamed_task__/Iteration 26 +__unnamed_task__/MaxReturn -76.9273 +__unnamed_task__/MinReturn -110.985 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.73727 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 05:08:20 | [maml_trainer] epoch #27 | Sampling for adapation and meta-testing... +2025-04-04 05:12:00 | [maml_trainer] epoch #27 | Finished meta-testing... +2025-04-04 05:12:00 | [maml_trainer] epoch #27 | Saving snapshot... +2025-04-04 05:12:20 | [maml_trainer] epoch #27 | Saved +2025-04-04 05:12:20 | [maml_trainer] epoch #27 | Time 45184.23 s +2025-04-04 05:12:20 | [maml_trainer] epoch #27 | EpochTime 1568.47 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -44.1012 +Average/AverageReturn -92.8233 +Average/Iteration 27 +Average/MaxReturn -68.4292 +Average/MinReturn -115.748 +Average/NumEpisodes 120 +Average/StdReturn 8.0963 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95656 +GaussianMLPPolicy/KLAfter 0.00802317 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.77399e-05 +GaussianMLPPolicy/LossBefore 9.29832e-09 +GaussianMLPPolicy/dLoss -2.77306e-05 +Iteration 27 +MetaTest/Average/AverageDiscountedReturn -92.0104 +MetaTest/Average/AverageReturn -92.0104 +MetaTest/Average/Iteration 27 +MetaTest/Average/MaxReturn -73.732 +MetaTest/Average/MinReturn -105.975 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.55389 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -92.0104 +MetaTest/__unnamed_task__/AverageReturn -92.0104 +MetaTest/__unnamed_task__/Iteration 27 +MetaTest/__unnamed_task__/MaxReturn -73.732 +MetaTest/__unnamed_task__/MinReturn -105.975 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.55389 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.344e+06 +__unnamed_task__/AverageDiscountedReturn -44.1012 +__unnamed_task__/AverageReturn -92.8233 +__unnamed_task__/Iteration 27 +__unnamed_task__/MaxReturn -68.4292 +__unnamed_task__/MinReturn -115.748 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.0963 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 05:34:22 | [maml_trainer] epoch #28 | Sampling for adapation and meta-testing... +2025-04-04 05:38:01 | [maml_trainer] epoch #28 | Finished meta-testing... +2025-04-04 05:38:01 | [maml_trainer] epoch #28 | Saving snapshot... +2025-04-04 05:38:20 | [maml_trainer] epoch #28 | Saved +2025-04-04 05:38:20 | [maml_trainer] epoch #28 | Time 46744.28 s +2025-04-04 05:38:20 | [maml_trainer] epoch #28 | EpochTime 1560.05 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -42.6438 +Average/AverageReturn -89.2431 +Average/Iteration 28 +Average/MaxReturn -67.3316 +Average/MinReturn -109.917 +Average/NumEpisodes 120 +Average/StdReturn 8.56009 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95648 +GaussianMLPPolicy/KLAfter 0.00765783 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.50815e-05 +GaussianMLPPolicy/LossBefore 2.98023e-09 +GaussianMLPPolicy/dLoss 5.50845e-05 +Iteration 28 +MetaTest/Average/AverageDiscountedReturn -89.1382 +MetaTest/Average/AverageReturn -89.1382 +MetaTest/Average/Iteration 28 +MetaTest/Average/MaxReturn -78.5266 +MetaTest/Average/MinReturn -99.7064 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.78137 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -89.1382 +MetaTest/__unnamed_task__/AverageReturn -89.1382 +MetaTest/__unnamed_task__/Iteration 28 +MetaTest/__unnamed_task__/MaxReturn -78.5266 +MetaTest/__unnamed_task__/MinReturn -99.7064 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.78137 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.392e+06 +__unnamed_task__/AverageDiscountedReturn -42.6438 +__unnamed_task__/AverageReturn -89.2431 +__unnamed_task__/Iteration 28 +__unnamed_task__/MaxReturn -67.3316 +__unnamed_task__/MinReturn -109.917 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.56009 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 06:00:13 | [maml_trainer] epoch #29 | Sampling for adapation and meta-testing... +2025-04-04 06:03:55 | [maml_trainer] epoch #29 | Finished meta-testing... +2025-04-04 06:03:55 | [maml_trainer] epoch #29 | Saving snapshot... +2025-04-04 06:04:15 | [maml_trainer] epoch #29 | Saved +2025-04-04 06:04:15 | [maml_trainer] epoch #29 | Time 48299.58 s +2025-04-04 06:04:15 | [maml_trainer] epoch #29 | EpochTime 1555.30 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -41.9964 +Average/AverageReturn -87.1991 +Average/Iteration 29 +Average/MaxReturn -66.646 +Average/MinReturn -114.347 +Average/NumEpisodes 120 +Average/StdReturn 8.71402 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95682 +GaussianMLPPolicy/KLAfter 0.00871886 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000174274 +GaussianMLPPolicy/LossBefore 6.75519e-10 +GaussianMLPPolicy/dLoss 0.000174275 +Iteration 29 +MetaTest/Average/AverageDiscountedReturn -83.9129 +MetaTest/Average/AverageReturn -83.9129 +MetaTest/Average/Iteration 29 +MetaTest/Average/MaxReturn -59.8647 +MetaTest/Average/MinReturn -106.127 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.79928 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -83.9129 +MetaTest/__unnamed_task__/AverageReturn -83.9129 +MetaTest/__unnamed_task__/Iteration 29 +MetaTest/__unnamed_task__/MaxReturn -59.8647 +MetaTest/__unnamed_task__/MinReturn -106.127 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.79928 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.44e+06 +__unnamed_task__/AverageDiscountedReturn -41.9964 +__unnamed_task__/AverageReturn -87.1991 +__unnamed_task__/Iteration 29 +__unnamed_task__/MaxReturn -66.646 +__unnamed_task__/MinReturn -114.347 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.71402 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 06:26:45 | [maml_trainer] epoch #30 | Sampling for adapation and meta-testing... +2025-04-04 06:30:30 | [maml_trainer] epoch #30 | Finished meta-testing... +2025-04-04 06:30:30 | [maml_trainer] epoch #30 | Saving snapshot... +2025-04-04 06:30:49 | [maml_trainer] epoch #30 | Saved +2025-04-04 06:30:49 | [maml_trainer] epoch #30 | Time 49893.91 s +2025-04-04 06:30:49 | [maml_trainer] epoch #30 | EpochTime 1594.33 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -41.3333 +Average/AverageReturn -85.2132 +Average/Iteration 30 +Average/MaxReturn -64.4476 +Average/MinReturn -105.606 +Average/NumEpisodes 120 +Average/StdReturn 8.9988 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95642 +GaussianMLPPolicy/KLAfter 0.00406935 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.62731e-05 +GaussianMLPPolicy/LossBefore 2.00272e-08 +GaussianMLPPolicy/dLoss 6.62931e-05 +Iteration 30 +MetaTest/Average/AverageDiscountedReturn -84.3896 +MetaTest/Average/AverageReturn -84.3896 +MetaTest/Average/Iteration 30 +MetaTest/Average/MaxReturn -69.9504 +MetaTest/Average/MinReturn -107.841 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.6824 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -84.3896 +MetaTest/__unnamed_task__/AverageReturn -84.3896 +MetaTest/__unnamed_task__/Iteration 30 +MetaTest/__unnamed_task__/MaxReturn -69.9504 +MetaTest/__unnamed_task__/MinReturn -107.841 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.6824 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.488e+06 +__unnamed_task__/AverageDiscountedReturn -41.3333 +__unnamed_task__/AverageReturn -85.2132 +__unnamed_task__/Iteration 30 +__unnamed_task__/MaxReturn -64.4476 +__unnamed_task__/MinReturn -105.606 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.9988 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 06:53:11 | [maml_trainer] epoch #31 | Sampling for adapation and meta-testing... +2025-04-04 06:56:55 | [maml_trainer] epoch #31 | Finished meta-testing... +2025-04-04 06:56:55 | [maml_trainer] epoch #31 | Saving snapshot... +2025-04-04 06:57:14 | [maml_trainer] epoch #31 | Saved +2025-04-04 06:57:14 | [maml_trainer] epoch #31 | Time 51478.91 s +2025-04-04 06:57:14 | [maml_trainer] epoch #31 | EpochTime 1585.00 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -40.2717 +Average/AverageReturn -82.7033 +Average/Iteration 31 +Average/MaxReturn -64.6415 +Average/MinReturn -103.064 +Average/NumEpisodes 120 +Average/StdReturn 7.61241 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95682 +GaussianMLPPolicy/KLAfter 0.00656332 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.86726e-05 +GaussianMLPPolicy/LossBefore 4.92732e-09 +GaussianMLPPolicy/dLoss 4.86775e-05 +Iteration 31 +MetaTest/Average/AverageDiscountedReturn -84.5883 +MetaTest/Average/AverageReturn -84.5883 +MetaTest/Average/Iteration 31 +MetaTest/Average/MaxReturn -71.4005 +MetaTest/Average/MinReturn -101.525 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.922 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -84.5883 +MetaTest/__unnamed_task__/AverageReturn -84.5883 +MetaTest/__unnamed_task__/Iteration 31 +MetaTest/__unnamed_task__/MaxReturn -71.4005 +MetaTest/__unnamed_task__/MinReturn -101.525 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.922 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.536e+06 +__unnamed_task__/AverageDiscountedReturn -40.2717 +__unnamed_task__/AverageReturn -82.7033 +__unnamed_task__/Iteration 31 +__unnamed_task__/MaxReturn -64.6415 +__unnamed_task__/MinReturn -103.064 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.61241 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 07:19:47 | [maml_trainer] epoch #32 | Sampling for adapation and meta-testing... +2025-04-04 07:23:34 | [maml_trainer] epoch #32 | Finished meta-testing... +2025-04-04 07:23:34 | [maml_trainer] epoch #32 | Saving snapshot... +2025-04-04 07:23:53 | [maml_trainer] epoch #32 | Saved +2025-04-04 07:23:53 | [maml_trainer] epoch #32 | Time 53077.55 s +2025-04-04 07:23:53 | [maml_trainer] epoch #32 | EpochTime 1598.63 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -39.9499 +Average/AverageReturn -81.6193 +Average/Iteration 32 +Average/MaxReturn -62.7162 +Average/MinReturn -102.906 +Average/NumEpisodes 120 +Average/StdReturn 8.34765 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95716 +GaussianMLPPolicy/KLAfter 0.00322622 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.41827e-05 +GaussianMLPPolicy/LossBefore -3.21865e-09 +GaussianMLPPolicy/dLoss 6.41795e-05 +Iteration 32 +MetaTest/Average/AverageDiscountedReturn -79.8778 +MetaTest/Average/AverageReturn -79.8778 +MetaTest/Average/Iteration 32 +MetaTest/Average/MaxReturn -62.1972 +MetaTest/Average/MinReturn -102.935 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.5407 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -79.8778 +MetaTest/__unnamed_task__/AverageReturn -79.8778 +MetaTest/__unnamed_task__/Iteration 32 +MetaTest/__unnamed_task__/MaxReturn -62.1972 +MetaTest/__unnamed_task__/MinReturn -102.935 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.5407 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.584e+06 +__unnamed_task__/AverageDiscountedReturn -39.9499 +__unnamed_task__/AverageReturn -81.6193 +__unnamed_task__/Iteration 32 +__unnamed_task__/MaxReturn -62.7162 +__unnamed_task__/MinReturn -102.906 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.34765 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 07:46:13 | [maml_trainer] epoch #33 | Sampling for adapation and meta-testing... +2025-04-04 07:50:01 | [maml_trainer] epoch #33 | Finished meta-testing... +2025-04-04 07:50:01 | [maml_trainer] epoch #33 | Saving snapshot... +2025-04-04 07:50:20 | [maml_trainer] epoch #33 | Saved +2025-04-04 07:50:20 | [maml_trainer] epoch #33 | Time 54664.72 s +2025-04-04 07:50:20 | [maml_trainer] epoch #33 | EpochTime 1587.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -39.2009 +Average/AverageReturn -80.0689 +Average/Iteration 33 +Average/MaxReturn -54.9197 +Average/MinReturn -107.625 +Average/NumEpisodes 120 +Average/StdReturn 9.51811 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95612 +GaussianMLPPolicy/KLAfter 0.00538882 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.85316e-05 +GaussianMLPPolicy/LossBefore 6.35783e-09 +GaussianMLPPolicy/dLoss 7.8538e-05 +Iteration 33 +MetaTest/Average/AverageDiscountedReturn -78.429 +MetaTest/Average/AverageReturn -78.429 +MetaTest/Average/Iteration 33 +MetaTest/Average/MaxReturn -58.9209 +MetaTest/Average/MinReturn -90.7865 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.2176 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -78.429 +MetaTest/__unnamed_task__/AverageReturn -78.429 +MetaTest/__unnamed_task__/Iteration 33 +MetaTest/__unnamed_task__/MaxReturn -58.9209 +MetaTest/__unnamed_task__/MinReturn -90.7865 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.2176 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.632e+06 +__unnamed_task__/AverageDiscountedReturn -39.2009 +__unnamed_task__/AverageReturn -80.0689 +__unnamed_task__/Iteration 33 +__unnamed_task__/MaxReturn -54.9197 +__unnamed_task__/MinReturn -107.625 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.51811 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 08:12:46 | [maml_trainer] epoch #34 | Sampling for adapation and meta-testing... +2025-04-04 08:16:33 | [maml_trainer] epoch #34 | Finished meta-testing... +2025-04-04 08:16:33 | [maml_trainer] epoch #34 | Saving snapshot... +2025-04-04 08:16:53 | [maml_trainer] epoch #34 | Saved +2025-04-04 08:16:53 | [maml_trainer] epoch #34 | Time 56256.98 s +2025-04-04 08:16:53 | [maml_trainer] epoch #34 | EpochTime 1592.26 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -38.6068 +Average/AverageReturn -78.6658 +Average/Iteration 34 +Average/MaxReturn -59.3901 +Average/MinReturn -105.74 +Average/NumEpisodes 120 +Average/StdReturn 9.40517 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95645 +GaussianMLPPolicy/KLAfter 0.00682468 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.89031e-05 +GaussianMLPPolicy/LossBefore 4.80811e-09 +GaussianMLPPolicy/dLoss -5.88982e-05 +Iteration 34 +MetaTest/Average/AverageDiscountedReturn -76.903 +MetaTest/Average/AverageReturn -76.903 +MetaTest/Average/Iteration 34 +MetaTest/Average/MaxReturn -61.7765 +MetaTest/Average/MinReturn -99.8302 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.13914 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -76.903 +MetaTest/__unnamed_task__/AverageReturn -76.903 +MetaTest/__unnamed_task__/Iteration 34 +MetaTest/__unnamed_task__/MaxReturn -61.7765 +MetaTest/__unnamed_task__/MinReturn -99.8302 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.13914 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.68e+06 +__unnamed_task__/AverageDiscountedReturn -38.6068 +__unnamed_task__/AverageReturn -78.6658 +__unnamed_task__/Iteration 34 +__unnamed_task__/MaxReturn -59.3901 +__unnamed_task__/MinReturn -105.74 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.40517 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 08:39:50 | [maml_trainer] epoch #35 | Sampling for adapation and meta-testing... +2025-04-04 08:43:40 | [maml_trainer] epoch #35 | Finished meta-testing... +2025-04-04 08:43:40 | [maml_trainer] epoch #35 | Saving snapshot... +2025-04-04 08:44:00 | [maml_trainer] epoch #35 | Saved +2025-04-04 08:44:00 | [maml_trainer] epoch #35 | Time 57884.40 s +2025-04-04 08:44:00 | [maml_trainer] epoch #35 | EpochTime 1627.41 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -38.063 +Average/AverageReturn -77.1499 +Average/Iteration 35 +Average/MaxReturn -59.0097 +Average/MinReturn -97.9927 +Average/NumEpisodes 120 +Average/StdReturn 8.21979 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95703 +GaussianMLPPolicy/KLAfter 0.00651828 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.70069e-05 +GaussianMLPPolicy/LossBefore 9.17912e-09 +GaussianMLPPolicy/dLoss 2.70161e-05 +Iteration 35 +MetaTest/Average/AverageDiscountedReturn -79.0295 +MetaTest/Average/AverageReturn -79.0295 +MetaTest/Average/Iteration 35 +MetaTest/Average/MaxReturn -58.6314 +MetaTest/Average/MinReturn -97.3986 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.47268 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -79.0295 +MetaTest/__unnamed_task__/AverageReturn -79.0295 +MetaTest/__unnamed_task__/Iteration 35 +MetaTest/__unnamed_task__/MaxReturn -58.6314 +MetaTest/__unnamed_task__/MinReturn -97.3986 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.47268 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.728e+06 +__unnamed_task__/AverageDiscountedReturn -38.063 +__unnamed_task__/AverageReturn -77.1499 +__unnamed_task__/Iteration 35 +__unnamed_task__/MaxReturn -59.0097 +__unnamed_task__/MinReturn -97.9927 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.21979 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 09:07:10 | [maml_trainer] epoch #36 | Sampling for adapation and meta-testing... +2025-04-04 09:11:00 | [maml_trainer] epoch #36 | Finished meta-testing... +2025-04-04 09:11:00 | [maml_trainer] epoch #36 | Saving snapshot... +2025-04-04 09:11:19 | [maml_trainer] epoch #36 | Saved +2025-04-04 09:11:19 | [maml_trainer] epoch #36 | Time 59523.46 s +2025-04-04 09:11:19 | [maml_trainer] epoch #36 | EpochTime 1639.06 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -37.4035 +Average/AverageReturn -75.1504 +Average/Iteration 36 +Average/MaxReturn -55.0235 +Average/MinReturn -97.1303 +Average/NumEpisodes 120 +Average/StdReturn 8.49267 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9578 +GaussianMLPPolicy/KLAfter 0.00653371 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000135147 +GaussianMLPPolicy/LossBefore -5.08626e-09 +GaussianMLPPolicy/dLoss 0.000135142 +Iteration 36 +MetaTest/Average/AverageDiscountedReturn -74.6331 +MetaTest/Average/AverageReturn -74.6331 +MetaTest/Average/Iteration 36 +MetaTest/Average/MaxReturn -59.3095 +MetaTest/Average/MinReturn -91.572 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.4263 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -74.6331 +MetaTest/__unnamed_task__/AverageReturn -74.6331 +MetaTest/__unnamed_task__/Iteration 36 +MetaTest/__unnamed_task__/MaxReturn -59.3095 +MetaTest/__unnamed_task__/MinReturn -91.572 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.4263 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.776e+06 +__unnamed_task__/AverageDiscountedReturn -37.4035 +__unnamed_task__/AverageReturn -75.1504 +__unnamed_task__/Iteration 36 +__unnamed_task__/MaxReturn -55.0235 +__unnamed_task__/MinReturn -97.1303 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.49267 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 09:34:13 | [maml_trainer] epoch #37 | Sampling for adapation and meta-testing... +2025-04-04 09:38:00 | [maml_trainer] epoch #37 | Finished meta-testing... +2025-04-04 09:38:00 | [maml_trainer] epoch #37 | Saving snapshot... +2025-04-04 09:38:19 | [maml_trainer] epoch #37 | Saved +2025-04-04 09:38:19 | [maml_trainer] epoch #37 | Time 61143.74 s +2025-04-04 09:38:19 | [maml_trainer] epoch #37 | EpochTime 1620.28 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -36.713 +Average/AverageReturn -74.3926 +Average/Iteration 37 +Average/MaxReturn -57.8871 +Average/MinReturn -99.0695 +Average/NumEpisodes 120 +Average/StdReturn 8.21299 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95776 +GaussianMLPPolicy/KLAfter 0.00383585 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000131952 +GaussianMLPPolicy/LossBefore -2.74181e-09 +GaussianMLPPolicy/dLoss -0.000131955 +Iteration 37 +MetaTest/Average/AverageDiscountedReturn -76.7123 +MetaTest/Average/AverageReturn -76.7123 +MetaTest/Average/Iteration 37 +MetaTest/Average/MaxReturn -63.0083 +MetaTest/Average/MinReturn -94.2631 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.47775 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -76.7123 +MetaTest/__unnamed_task__/AverageReturn -76.7123 +MetaTest/__unnamed_task__/Iteration 37 +MetaTest/__unnamed_task__/MaxReturn -63.0083 +MetaTest/__unnamed_task__/MinReturn -94.2631 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.47775 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.824e+06 +__unnamed_task__/AverageDiscountedReturn -36.713 +__unnamed_task__/AverageReturn -74.3926 +__unnamed_task__/Iteration 37 +__unnamed_task__/MaxReturn -57.8871 +__unnamed_task__/MinReturn -99.0695 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.21299 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 10:01:08 | [maml_trainer] epoch #38 | Sampling for adapation and meta-testing... +2025-04-04 10:04:56 | [maml_trainer] epoch #38 | Finished meta-testing... +2025-04-04 10:04:56 | [maml_trainer] epoch #38 | Saving snapshot... +2025-04-04 10:05:16 | [maml_trainer] epoch #38 | Saved +2025-04-04 10:05:16 | [maml_trainer] epoch #38 | Time 62760.53 s +2025-04-04 10:05:16 | [maml_trainer] epoch #38 | EpochTime 1616.78 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -36.5022 +Average/AverageReturn -73.4496 +Average/Iteration 38 +Average/MaxReturn -58.1056 +Average/MinReturn -96.0145 +Average/NumEpisodes 120 +Average/StdReturn 7.77252 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95539 +GaussianMLPPolicy/KLAfter 0.00389101 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.53233e-05 +GaussianMLPPolicy/LossBefore 2.1855e-09 +GaussianMLPPolicy/dLoss -2.53211e-05 +Iteration 38 +MetaTest/Average/AverageDiscountedReturn -71.0726 +MetaTest/Average/AverageReturn -71.0726 +MetaTest/Average/Iteration 38 +MetaTest/Average/MaxReturn -56.8097 +MetaTest/Average/MinReturn -86.2047 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.54505 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -71.0726 +MetaTest/__unnamed_task__/AverageReturn -71.0726 +MetaTest/__unnamed_task__/Iteration 38 +MetaTest/__unnamed_task__/MaxReturn -56.8097 +MetaTest/__unnamed_task__/MinReturn -86.2047 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.54505 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.872e+06 +__unnamed_task__/AverageDiscountedReturn -36.5022 +__unnamed_task__/AverageReturn -73.4496 +__unnamed_task__/Iteration 38 +__unnamed_task__/MaxReturn -58.1056 +__unnamed_task__/MinReturn -96.0145 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.77252 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 10:28:22 | [maml_trainer] epoch #39 | Sampling for adapation and meta-testing... +2025-04-04 10:32:10 | [maml_trainer] epoch #39 | Finished meta-testing... +2025-04-04 10:32:10 | [maml_trainer] epoch #39 | Saving snapshot... +2025-04-04 10:32:29 | [maml_trainer] epoch #39 | Saved +2025-04-04 10:32:29 | [maml_trainer] epoch #39 | Time 64393.83 s +2025-04-04 10:32:29 | [maml_trainer] epoch #39 | EpochTime 1633.30 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.934 +Average/AverageReturn -74.8312 +Average/Iteration 39 +Average/MaxReturn -54.712 +Average/MinReturn -100.583 +Average/NumEpisodes 120 +Average/StdReturn 9.56084 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95321 +GaussianMLPPolicy/KLAfter 0.00183818 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.02884e-05 +GaussianMLPPolicy/LossBefore 9.93411e-10 +GaussianMLPPolicy/dLoss 2.02894e-05 +Iteration 39 +MetaTest/Average/AverageDiscountedReturn -77.3482 +MetaTest/Average/AverageReturn -77.3482 +MetaTest/Average/Iteration 39 +MetaTest/Average/MaxReturn -61.032 +MetaTest/Average/MinReturn -94.896 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.5234 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -77.3482 +MetaTest/__unnamed_task__/AverageReturn -77.3482 +MetaTest/__unnamed_task__/Iteration 39 +MetaTest/__unnamed_task__/MaxReturn -61.032 +MetaTest/__unnamed_task__/MinReturn -94.896 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.5234 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.92e+06 +__unnamed_task__/AverageDiscountedReturn -36.934 +__unnamed_task__/AverageReturn -74.8312 +__unnamed_task__/Iteration 39 +__unnamed_task__/MaxReturn -54.712 +__unnamed_task__/MinReturn -100.583 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.56084 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 10:55:37 | [maml_trainer] epoch #40 | Sampling for adapation and meta-testing... +2025-04-04 10:59:28 | [maml_trainer] epoch #40 | Finished meta-testing... +2025-04-04 10:59:28 | [maml_trainer] epoch #40 | Saving snapshot... +2025-04-04 10:59:48 | [maml_trainer] epoch #40 | Saved +2025-04-04 10:59:48 | [maml_trainer] epoch #40 | Time 66032.27 s +2025-04-04 10:59:48 | [maml_trainer] epoch #40 | EpochTime 1638.43 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -37.0681 +Average/AverageReturn -75.2762 +Average/Iteration 40 +Average/MaxReturn -57.8028 +Average/MinReturn -105.55 +Average/NumEpisodes 120 +Average/StdReturn 9.24602 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95169 +GaussianMLPPolicy/KLAfter 0.00170484 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.5121e-05 +GaussianMLPPolicy/LossBefore 2.30471e-09 +GaussianMLPPolicy/dLoss 3.51233e-05 +Iteration 40 +MetaTest/Average/AverageDiscountedReturn -80.1382 +MetaTest/Average/AverageReturn -80.1382 +MetaTest/Average/Iteration 40 +MetaTest/Average/MaxReturn -62.6461 +MetaTest/Average/MinReturn -104.53 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.80883 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -80.1382 +MetaTest/__unnamed_task__/AverageReturn -80.1382 +MetaTest/__unnamed_task__/Iteration 40 +MetaTest/__unnamed_task__/MaxReturn -62.6461 +MetaTest/__unnamed_task__/MinReturn -104.53 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.80883 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.968e+06 +__unnamed_task__/AverageDiscountedReturn -37.0681 +__unnamed_task__/AverageReturn -75.2762 +__unnamed_task__/Iteration 40 +__unnamed_task__/MaxReturn -57.8028 +__unnamed_task__/MinReturn -105.55 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.24602 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 11:22:49 | [maml_trainer] epoch #41 | Sampling for adapation and meta-testing... +2025-04-04 11:26:39 | [maml_trainer] epoch #41 | Finished meta-testing... +2025-04-04 11:26:39 | [maml_trainer] epoch #41 | Saving snapshot... +2025-04-04 11:26:59 | [maml_trainer] epoch #41 | Saved +2025-04-04 11:26:59 | [maml_trainer] epoch #41 | Time 67662.99 s +2025-04-04 11:26:59 | [maml_trainer] epoch #41 | EpochTime 1630.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.4298 +Average/AverageReturn -74.6512 +Average/Iteration 41 +Average/MaxReturn -53.6053 +Average/MinReturn -103.544 +Average/NumEpisodes 120 +Average/StdReturn 10.7455 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95177 +GaussianMLPPolicy/KLAfter 0.00128986 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.05066e-05 +GaussianMLPPolicy/LossBefore 1.86761e-09 +GaussianMLPPolicy/dLoss -3.05047e-05 +Iteration 41 +MetaTest/Average/AverageDiscountedReturn -70.1681 +MetaTest/Average/AverageReturn -70.1681 +MetaTest/Average/Iteration 41 +MetaTest/Average/MaxReturn -56.0195 +MetaTest/Average/MinReturn -106.836 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.3204 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -70.1681 +MetaTest/__unnamed_task__/AverageReturn -70.1681 +MetaTest/__unnamed_task__/Iteration 41 +MetaTest/__unnamed_task__/MaxReturn -56.0195 +MetaTest/__unnamed_task__/MinReturn -106.836 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.3204 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.016e+06 +__unnamed_task__/AverageDiscountedReturn -36.4298 +__unnamed_task__/AverageReturn -74.6512 +__unnamed_task__/Iteration 41 +__unnamed_task__/MaxReturn -53.6053 +__unnamed_task__/MinReturn -103.544 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.7455 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 11:50:01 | [maml_trainer] epoch #42 | Sampling for adapation and meta-testing... +2025-04-04 11:53:52 | [maml_trainer] epoch #42 | Finished meta-testing... +2025-04-04 11:53:52 | [maml_trainer] epoch #42 | Saving snapshot... +2025-04-04 11:54:12 | [maml_trainer] epoch #42 | Saved +2025-04-04 11:54:12 | [maml_trainer] epoch #42 | Time 69296.49 s +2025-04-04 11:54:12 | [maml_trainer] epoch #42 | EpochTime 1633.50 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.696 +Average/AverageReturn -74.9699 +Average/Iteration 42 +Average/MaxReturn -55.5582 +Average/MinReturn -98.5279 +Average/NumEpisodes 120 +Average/StdReturn 9.66568 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95059 +GaussianMLPPolicy/KLAfter 0.00171648 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.80605e-06 +GaussianMLPPolicy/LossBefore -1.64906e-08 +GaussianMLPPolicy/dLoss -5.82254e-06 +Iteration 42 +MetaTest/Average/AverageDiscountedReturn -73.799 +MetaTest/Average/AverageReturn -73.799 +MetaTest/Average/Iteration 42 +MetaTest/Average/MaxReturn -58.7446 +MetaTest/Average/MinReturn -105.728 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.904 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -73.799 +MetaTest/__unnamed_task__/AverageReturn -73.799 +MetaTest/__unnamed_task__/Iteration 42 +MetaTest/__unnamed_task__/MaxReturn -58.7446 +MetaTest/__unnamed_task__/MinReturn -105.728 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.904 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.064e+06 +__unnamed_task__/AverageDiscountedReturn -36.696 +__unnamed_task__/AverageReturn -74.9699 +__unnamed_task__/Iteration 42 +__unnamed_task__/MaxReturn -55.5582 +__unnamed_task__/MinReturn -98.5279 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.66568 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 12:17:18 | [maml_trainer] epoch #43 | Sampling for adapation and meta-testing... +2025-04-04 12:21:11 | [maml_trainer] epoch #43 | Finished meta-testing... +2025-04-04 12:21:11 | [maml_trainer] epoch #43 | Saving snapshot... +2025-04-04 12:21:31 | [maml_trainer] epoch #43 | Saved +2025-04-04 12:21:31 | [maml_trainer] epoch #43 | Time 70935.57 s +2025-04-04 12:21:31 | [maml_trainer] epoch #43 | EpochTime 1639.08 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -35.9761 +Average/AverageReturn -73.1482 +Average/Iteration 43 +Average/MaxReturn -56.8896 +Average/MinReturn -97.5414 +Average/NumEpisodes 120 +Average/StdReturn 9.60402 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95003 +GaussianMLPPolicy/KLAfter 0.00193456 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.47054e-06 +GaussianMLPPolicy/LossBefore 9.45727e-09 +GaussianMLPPolicy/dLoss 3.48e-06 +Iteration 43 +MetaTest/Average/AverageDiscountedReturn -70.6185 +MetaTest/Average/AverageReturn -70.6185 +MetaTest/Average/Iteration 43 +MetaTest/Average/MaxReturn -53.923 +MetaTest/Average/MinReturn -93.0957 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.6587 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -70.6185 +MetaTest/__unnamed_task__/AverageReturn -70.6185 +MetaTest/__unnamed_task__/Iteration 43 +MetaTest/__unnamed_task__/MaxReturn -53.923 +MetaTest/__unnamed_task__/MinReturn -93.0957 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.6587 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.112e+06 +__unnamed_task__/AverageDiscountedReturn -35.9761 +__unnamed_task__/AverageReturn -73.1482 +__unnamed_task__/Iteration 43 +__unnamed_task__/MaxReturn -56.8896 +__unnamed_task__/MinReturn -97.5414 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.60402 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 12:44:29 | [maml_trainer] epoch #44 | Sampling for adapation and meta-testing... +2025-04-04 12:48:22 | [maml_trainer] epoch #44 | Finished meta-testing... +2025-04-04 12:48:22 | [maml_trainer] epoch #44 | Saving snapshot... +2025-04-04 12:48:42 | [maml_trainer] epoch #44 | Saved +2025-04-04 12:48:42 | [maml_trainer] epoch #44 | Time 72566.12 s +2025-04-04 12:48:42 | [maml_trainer] epoch #44 | EpochTime 1630.54 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.2323 +Average/AverageReturn -73.7171 +Average/Iteration 44 +Average/MaxReturn -53.7007 +Average/MinReturn -98.203 +Average/NumEpisodes 120 +Average/StdReturn 9.89788 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94971 +GaussianMLPPolicy/KLAfter 0.00241179 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.47952e-06 +GaussianMLPPolicy/LossBefore 1.07288e-08 +GaussianMLPPolicy/dLoss -3.46879e-06 +Iteration 44 +MetaTest/Average/AverageDiscountedReturn -71.4342 +MetaTest/Average/AverageReturn -71.4342 +MetaTest/Average/Iteration 44 +MetaTest/Average/MaxReturn -59.2715 +MetaTest/Average/MinReturn -101.065 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.8327 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -71.4342 +MetaTest/__unnamed_task__/AverageReturn -71.4342 +MetaTest/__unnamed_task__/Iteration 44 +MetaTest/__unnamed_task__/MaxReturn -59.2715 +MetaTest/__unnamed_task__/MinReturn -101.065 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.8327 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.16e+06 +__unnamed_task__/AverageDiscountedReturn -36.2323 +__unnamed_task__/AverageReturn -73.7171 +__unnamed_task__/Iteration 44 +__unnamed_task__/MaxReturn -53.7007 +__unnamed_task__/MinReturn -98.203 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.89788 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 13:12:10 | [maml_trainer] epoch #45 | Sampling for adapation and meta-testing... +2025-04-04 13:16:00 | [maml_trainer] epoch #45 | Finished meta-testing... +2025-04-04 13:16:00 | [maml_trainer] epoch #45 | Saving snapshot... +2025-04-04 13:16:20 | [maml_trainer] epoch #45 | Saved +2025-04-04 13:16:20 | [maml_trainer] epoch #45 | Time 74224.00 s +2025-04-04 13:16:20 | [maml_trainer] epoch #45 | EpochTime 1657.88 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.079 +Average/AverageReturn -73.4313 +Average/Iteration 45 +Average/MaxReturn -54.8981 +Average/MinReturn -103.529 +Average/NumEpisodes 120 +Average/StdReturn 10.3505 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94852 +GaussianMLPPolicy/KLAfter 0.00277888 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.34211e-05 +GaussianMLPPolicy/LossBefore 6.35783e-10 +GaussianMLPPolicy/dLoss -5.34204e-05 +Iteration 45 +MetaTest/Average/AverageDiscountedReturn -72.3886 +MetaTest/Average/AverageReturn -72.3886 +MetaTest/Average/Iteration 45 +MetaTest/Average/MaxReturn -58.1897 +MetaTest/Average/MinReturn -90.204 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.73098 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -72.3886 +MetaTest/__unnamed_task__/AverageReturn -72.3886 +MetaTest/__unnamed_task__/Iteration 45 +MetaTest/__unnamed_task__/MaxReturn -58.1897 +MetaTest/__unnamed_task__/MinReturn -90.204 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.73098 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.208e+06 +__unnamed_task__/AverageDiscountedReturn -36.079 +__unnamed_task__/AverageReturn -73.4313 +__unnamed_task__/Iteration 45 +__unnamed_task__/MaxReturn -54.8981 +__unnamed_task__/MinReturn -103.529 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.3505 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 13:39:57 | [maml_trainer] epoch #46 | Sampling for adapation and meta-testing... +2025-04-04 13:43:50 | [maml_trainer] epoch #46 | Finished meta-testing... +2025-04-04 13:43:50 | [maml_trainer] epoch #46 | Saving snapshot... +2025-04-04 13:44:09 | [maml_trainer] epoch #46 | Saved +2025-04-04 13:44:09 | [maml_trainer] epoch #46 | Time 75893.91 s +2025-04-04 13:44:09 | [maml_trainer] epoch #46 | EpochTime 1669.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -35.5808 +Average/AverageReturn -72.3932 +Average/Iteration 46 +Average/MaxReturn -56.2675 +Average/MinReturn -113.119 +Average/NumEpisodes 120 +Average/StdReturn 10.415 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94718 +GaussianMLPPolicy/KLAfter 0.00133236 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.77545e-05 +GaussianMLPPolicy/LossBefore -1.56164e-08 +GaussianMLPPolicy/dLoss 3.77389e-05 +Iteration 46 +MetaTest/Average/AverageDiscountedReturn -75.7235 +MetaTest/Average/AverageReturn -75.7235 +MetaTest/Average/Iteration 46 +MetaTest/Average/MaxReturn -56.0302 +MetaTest/Average/MinReturn -101.206 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.1313 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -75.7235 +MetaTest/__unnamed_task__/AverageReturn -75.7235 +MetaTest/__unnamed_task__/Iteration 46 +MetaTest/__unnamed_task__/MaxReturn -56.0302 +MetaTest/__unnamed_task__/MinReturn -101.206 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.1313 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.256e+06 +__unnamed_task__/AverageDiscountedReturn -35.5808 +__unnamed_task__/AverageReturn -72.3932 +__unnamed_task__/Iteration 46 +__unnamed_task__/MaxReturn -56.2675 +__unnamed_task__/MinReturn -113.119 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.415 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 14:07:18 | [maml_trainer] epoch #47 | Sampling for adapation and meta-testing... +2025-04-04 14:11:11 | [maml_trainer] epoch #47 | Finished meta-testing... +2025-04-04 14:11:11 | [maml_trainer] epoch #47 | Saving snapshot... +2025-04-04 14:11:31 | [maml_trainer] epoch #47 | Saved +2025-04-04 14:11:31 | [maml_trainer] epoch #47 | Time 77535.32 s +2025-04-04 14:11:31 | [maml_trainer] epoch #47 | EpochTime 1641.41 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -36.2716 +Average/AverageReturn -74.8553 +Average/Iteration 47 +Average/MaxReturn -56.9895 +Average/MinReturn -107.34 +Average/NumEpisodes 120 +Average/StdReturn 11.3824 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9457 +GaussianMLPPolicy/KLAfter 0.00150252 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.88057e-05 +GaussianMLPPolicy/LossBefore -5.40415e-09 +GaussianMLPPolicy/dLoss -9.88111e-05 +Iteration 47 +MetaTest/Average/AverageDiscountedReturn -71.2412 +MetaTest/Average/AverageReturn -71.2412 +MetaTest/Average/Iteration 47 +MetaTest/Average/MaxReturn -52.5486 +MetaTest/Average/MinReturn -94.137 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.3096 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -71.2412 +MetaTest/__unnamed_task__/AverageReturn -71.2412 +MetaTest/__unnamed_task__/Iteration 47 +MetaTest/__unnamed_task__/MaxReturn -52.5486 +MetaTest/__unnamed_task__/MinReturn -94.137 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.3096 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.304e+06 +__unnamed_task__/AverageDiscountedReturn -36.2716 +__unnamed_task__/AverageReturn -74.8553 +__unnamed_task__/Iteration 47 +__unnamed_task__/MaxReturn -56.9895 +__unnamed_task__/MinReturn -107.34 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.3824 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 14:34:49 | [maml_trainer] epoch #48 | Sampling for adapation and meta-testing... +2025-04-04 14:38:41 | [maml_trainer] epoch #48 | Finished meta-testing... +2025-04-04 14:38:41 | [maml_trainer] epoch #48 | Saving snapshot... +2025-04-04 14:39:00 | [maml_trainer] epoch #48 | Saved +2025-04-04 14:39:00 | [maml_trainer] epoch #48 | Time 79184.78 s +2025-04-04 14:39:00 | [maml_trainer] epoch #48 | EpochTime 1649.45 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -35.8446 +Average/AverageReturn -73.7913 +Average/Iteration 48 +Average/MaxReturn -53.4425 +Average/MinReturn -99.0771 +Average/NumEpisodes 120 +Average/StdReturn 10.5379 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94423 +GaussianMLPPolicy/KLAfter 0.00155773 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.22221e-05 +GaussianMLPPolicy/LossBefore 4.92732e-09 +GaussianMLPPolicy/dLoss -2.22172e-05 +Iteration 48 +MetaTest/Average/AverageDiscountedReturn -69.1756 +MetaTest/Average/AverageReturn -69.1756 +MetaTest/Average/Iteration 48 +MetaTest/Average/MaxReturn -52.7117 +MetaTest/Average/MinReturn -98.2236 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.5162 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -69.1756 +MetaTest/__unnamed_task__/AverageReturn -69.1756 +MetaTest/__unnamed_task__/Iteration 48 +MetaTest/__unnamed_task__/MaxReturn -52.7117 +MetaTest/__unnamed_task__/MinReturn -98.2236 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.5162 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.352e+06 +__unnamed_task__/AverageDiscountedReturn -35.8446 +__unnamed_task__/AverageReturn -73.7913 +__unnamed_task__/Iteration 48 +__unnamed_task__/MaxReturn -53.4425 +__unnamed_task__/MinReturn -99.0771 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.5379 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 15:02:04 | [maml_trainer] epoch #49 | Sampling for adapation and meta-testing... +2025-04-04 15:05:58 | [maml_trainer] epoch #49 | Finished meta-testing... +2025-04-04 15:05:58 | [maml_trainer] epoch #49 | Saving snapshot... +2025-04-04 15:06:18 | [maml_trainer] epoch #49 | Saved +2025-04-04 15:06:18 | [maml_trainer] epoch #49 | Time 80822.73 s +2025-04-04 15:06:18 | [maml_trainer] epoch #49 | EpochTime 1637.95 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -35.7876 +Average/AverageReturn -73.1591 +Average/Iteration 49 +Average/MaxReturn -56.6736 +Average/MinReturn -103.059 +Average/NumEpisodes 120 +Average/StdReturn 10.5127 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94541 +GaussianMLPPolicy/KLAfter 0.00207737 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.96533e-05 +GaussianMLPPolicy/LossBefore -3.85443e-09 +GaussianMLPPolicy/dLoss 3.96495e-05 +Iteration 49 +MetaTest/Average/AverageDiscountedReturn -73.6875 +MetaTest/Average/AverageReturn -73.6875 +MetaTest/Average/Iteration 49 +MetaTest/Average/MaxReturn -60.243 +MetaTest/Average/MinReturn -95.0189 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.66312 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -73.6875 +MetaTest/__unnamed_task__/AverageReturn -73.6875 +MetaTest/__unnamed_task__/Iteration 49 +MetaTest/__unnamed_task__/MaxReturn -60.243 +MetaTest/__unnamed_task__/MinReturn -95.0189 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.66312 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.4e+06 +__unnamed_task__/AverageDiscountedReturn -35.7876 +__unnamed_task__/AverageReturn -73.1591 +__unnamed_task__/Iteration 49 +__unnamed_task__/MaxReturn -56.6736 +__unnamed_task__/MinReturn -103.059 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.5127 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 15:29:47 | [maml_trainer] epoch #50 | Sampling for adapation and meta-testing... +2025-04-04 15:33:41 | [maml_trainer] epoch #50 | Finished meta-testing... +2025-04-04 15:33:41 | [maml_trainer] epoch #50 | Saving snapshot... +2025-04-04 15:34:01 | [maml_trainer] epoch #50 | Saved +2025-04-04 15:34:01 | [maml_trainer] epoch #50 | Time 82485.94 s +2025-04-04 15:34:01 | [maml_trainer] epoch #50 | EpochTime 1663.20 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -36.0038 +Average/AverageReturn -74.0011 +Average/Iteration 50 +Average/MaxReturn -54.3492 +Average/MinReturn -95.4378 +Average/NumEpisodes 120 +Average/StdReturn 10.149 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94679 +GaussianMLPPolicy/KLAfter 0.00362502 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.94505e-05 +GaussianMLPPolicy/LossBefore -2.22524e-09 +GaussianMLPPolicy/dLoss 9.94482e-05 +Iteration 50 +MetaTest/Average/AverageDiscountedReturn -69.5808 +MetaTest/Average/AverageReturn -69.5808 +MetaTest/Average/Iteration 50 +MetaTest/Average/MaxReturn -53.5694 +MetaTest/Average/MinReturn -85.6434 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.16393 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -69.5808 +MetaTest/__unnamed_task__/AverageReturn -69.5808 +MetaTest/__unnamed_task__/Iteration 50 +MetaTest/__unnamed_task__/MaxReturn -53.5694 +MetaTest/__unnamed_task__/MinReturn -85.6434 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.16393 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.448e+06 +__unnamed_task__/AverageDiscountedReturn -36.0038 +__unnamed_task__/AverageReturn -74.0011 +__unnamed_task__/Iteration 50 +__unnamed_task__/MaxReturn -54.3492 +__unnamed_task__/MinReturn -95.4378 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.149 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 15:57:35 | [maml_trainer] epoch #51 | Sampling for adapation and meta-testing... +2025-04-04 16:01:29 | [maml_trainer] epoch #51 | Finished meta-testing... +2025-04-04 16:01:29 | [maml_trainer] epoch #51 | Saving snapshot... +2025-04-04 16:01:49 | [maml_trainer] epoch #51 | Saved +2025-04-04 16:01:49 | [maml_trainer] epoch #51 | Time 84153.30 s +2025-04-04 16:01:49 | [maml_trainer] epoch #51 | EpochTime 1667.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -35.6681 +Average/AverageReturn -72.4079 +Average/Iteration 51 +Average/MaxReturn -52.4892 +Average/MinReturn -99.8819 +Average/NumEpisodes 120 +Average/StdReturn 10.329 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94924 +GaussianMLPPolicy/KLAfter 0.00425464 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.52394e-05 +GaussianMLPPolicy/LossBefore 1.27554e-08 +GaussianMLPPolicy/dLoss 8.52522e-05 +Iteration 51 +MetaTest/Average/AverageDiscountedReturn -73.0213 +MetaTest/Average/AverageReturn -73.0213 +MetaTest/Average/Iteration 51 +MetaTest/Average/MaxReturn -57.0488 +MetaTest/Average/MinReturn -94.0957 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.1165 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -73.0213 +MetaTest/__unnamed_task__/AverageReturn -73.0213 +MetaTest/__unnamed_task__/Iteration 51 +MetaTest/__unnamed_task__/MaxReturn -57.0488 +MetaTest/__unnamed_task__/MinReturn -94.0957 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.1165 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.496e+06 +__unnamed_task__/AverageDiscountedReturn -35.6681 +__unnamed_task__/AverageReturn -72.4079 +__unnamed_task__/Iteration 51 +__unnamed_task__/MaxReturn -52.4892 +__unnamed_task__/MinReturn -99.8819 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.329 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 16:24:58 | [maml_trainer] epoch #52 | Sampling for adapation and meta-testing... +2025-04-04 16:28:50 | [maml_trainer] epoch #52 | Finished meta-testing... +2025-04-04 16:28:50 | [maml_trainer] epoch #52 | Saving snapshot... +2025-04-04 16:29:11 | [maml_trainer] epoch #52 | Saved +2025-04-04 16:29:11 | [maml_trainer] epoch #52 | Time 85795.00 s +2025-04-04 16:29:11 | [maml_trainer] epoch #52 | EpochTime 1641.70 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -35.2794 +Average/AverageReturn -72.0024 +Average/Iteration 52 +Average/MaxReturn -52.1485 +Average/MinReturn -100.378 +Average/NumEpisodes 120 +Average/StdReturn 11.1225 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95205 +GaussianMLPPolicy/KLAfter 0.00437394 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.21149e-05 +GaussianMLPPolicy/LossBefore -1.00136e-08 +GaussianMLPPolicy/dLoss 2.21049e-05 +Iteration 52 +MetaTest/Average/AverageDiscountedReturn -71.6818 +MetaTest/Average/AverageReturn -71.6818 +MetaTest/Average/Iteration 52 +MetaTest/Average/MaxReturn -55.5237 +MetaTest/Average/MinReturn -85.7311 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.19347 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -71.6818 +MetaTest/__unnamed_task__/AverageReturn -71.6818 +MetaTest/__unnamed_task__/Iteration 52 +MetaTest/__unnamed_task__/MaxReturn -55.5237 +MetaTest/__unnamed_task__/MinReturn -85.7311 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.19347 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.544e+06 +__unnamed_task__/AverageDiscountedReturn -35.2794 +__unnamed_task__/AverageReturn -72.0024 +__unnamed_task__/Iteration 52 +__unnamed_task__/MaxReturn -52.1485 +__unnamed_task__/MinReturn -100.378 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.1225 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 16:52:36 | [maml_trainer] epoch #53 | Sampling for adapation and meta-testing... +2025-04-04 16:56:30 | [maml_trainer] epoch #53 | Finished meta-testing... +2025-04-04 16:56:30 | [maml_trainer] epoch #53 | Saving snapshot... +2025-04-04 16:56:50 | [maml_trainer] epoch #53 | Saved +2025-04-04 16:56:50 | [maml_trainer] epoch #53 | Time 87454.58 s +2025-04-04 16:56:50 | [maml_trainer] epoch #53 | EpochTime 1659.57 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.6968 +Average/AverageReturn -70.2331 +Average/Iteration 53 +Average/MaxReturn -50.5958 +Average/MinReturn -101.527 +Average/NumEpisodes 120 +Average/StdReturn 10.907 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95642 +GaussianMLPPolicy/KLAfter 0.00761887 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.00017468 +GaussianMLPPolicy/LossBefore -7.98702e-09 +GaussianMLPPolicy/dLoss 0.000174672 +Iteration 53 +MetaTest/Average/AverageDiscountedReturn -72.1521 +MetaTest/Average/AverageReturn -72.1521 +MetaTest/Average/Iteration 53 +MetaTest/Average/MaxReturn -55.2811 +MetaTest/Average/MinReturn -100.468 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.2806 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -72.1521 +MetaTest/__unnamed_task__/AverageReturn -72.1521 +MetaTest/__unnamed_task__/Iteration 53 +MetaTest/__unnamed_task__/MaxReturn -55.2811 +MetaTest/__unnamed_task__/MinReturn -100.468 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.2806 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.592e+06 +__unnamed_task__/AverageDiscountedReturn -34.6968 +__unnamed_task__/AverageReturn -70.2331 +__unnamed_task__/Iteration 53 +__unnamed_task__/MaxReturn -50.5958 +__unnamed_task__/MinReturn -101.527 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.907 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 17:20:19 | [maml_trainer] epoch #54 | Sampling for adapation and meta-testing... +2025-04-04 17:24:12 | [maml_trainer] epoch #54 | Finished meta-testing... +2025-04-04 17:24:12 | [maml_trainer] epoch #54 | Saving snapshot... +2025-04-04 17:24:31 | [maml_trainer] epoch #54 | Saved +2025-04-04 17:24:31 | [maml_trainer] epoch #54 | Time 89115.96 s +2025-04-04 17:24:31 | [maml_trainer] epoch #54 | EpochTime 1661.37 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -35.1745 +Average/AverageReturn -71.45 +Average/Iteration 54 +Average/MaxReturn -53.9973 +Average/MinReturn -108.566 +Average/NumEpisodes 120 +Average/StdReturn 11.175 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96083 +GaussianMLPPolicy/KLAfter 0.00769316 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.92302e-05 +GaussianMLPPolicy/LossBefore 8.0665e-09 +GaussianMLPPolicy/dLoss -3.92221e-05 +Iteration 54 +MetaTest/Average/AverageDiscountedReturn -77.3461 +MetaTest/Average/AverageReturn -77.3461 +MetaTest/Average/Iteration 54 +MetaTest/Average/MaxReturn -59.8536 +MetaTest/Average/MinReturn -87.9344 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.50901 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -77.3461 +MetaTest/__unnamed_task__/AverageReturn -77.3461 +MetaTest/__unnamed_task__/Iteration 54 +MetaTest/__unnamed_task__/MaxReturn -59.8536 +MetaTest/__unnamed_task__/MinReturn -87.9344 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.50901 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.64e+06 +__unnamed_task__/AverageDiscountedReturn -35.1745 +__unnamed_task__/AverageReturn -71.45 +__unnamed_task__/Iteration 54 +__unnamed_task__/MaxReturn -53.9973 +__unnamed_task__/MinReturn -108.566 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.175 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 17:47:42 | [maml_trainer] epoch #55 | Sampling for adapation and meta-testing... +2025-04-04 17:51:35 | [maml_trainer] epoch #55 | Finished meta-testing... +2025-04-04 17:51:35 | [maml_trainer] epoch #55 | Saving snapshot... +2025-04-04 17:51:54 | [maml_trainer] epoch #55 | Saved +2025-04-04 17:51:54 | [maml_trainer] epoch #55 | Time 90758.88 s +2025-04-04 17:51:54 | [maml_trainer] epoch #55 | EpochTime 1642.92 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.2941 +Average/AverageReturn -68.4049 +Average/Iteration 55 +Average/MaxReturn -50.3214 +Average/MinReturn -99.4283 +Average/NumEpisodes 120 +Average/StdReturn 10.4176 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96561 +GaussianMLPPolicy/KLAfter 0.00579663 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000196719 +GaussianMLPPolicy/LossBefore -1.13646e-08 +GaussianMLPPolicy/dLoss -0.00019673 +Iteration 55 +MetaTest/Average/AverageDiscountedReturn -73.3874 +MetaTest/Average/AverageReturn -73.3874 +MetaTest/Average/Iteration 55 +MetaTest/Average/MaxReturn -51.6261 +MetaTest/Average/MinReturn -127.245 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.1422 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -73.3874 +MetaTest/__unnamed_task__/AverageReturn -73.3874 +MetaTest/__unnamed_task__/Iteration 55 +MetaTest/__unnamed_task__/MaxReturn -51.6261 +MetaTest/__unnamed_task__/MinReturn -127.245 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.1422 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.688e+06 +__unnamed_task__/AverageDiscountedReturn -34.2941 +__unnamed_task__/AverageReturn -68.4049 +__unnamed_task__/Iteration 55 +__unnamed_task__/MaxReturn -50.3214 +__unnamed_task__/MinReturn -99.4283 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.4176 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 18:15:46 | [maml_trainer] epoch #56 | Sampling for adapation and meta-testing... +2025-04-04 18:19:46 | [maml_trainer] epoch #56 | Finished meta-testing... +2025-04-04 18:19:46 | [maml_trainer] epoch #56 | Saving snapshot... +2025-04-04 18:20:06 | [maml_trainer] epoch #56 | Saved +2025-04-04 18:20:06 | [maml_trainer] epoch #56 | Time 92450.02 s +2025-04-04 18:20:06 | [maml_trainer] epoch #56 | EpochTime 1691.14 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.6212 +Average/AverageReturn -70.0492 +Average/Iteration 56 +Average/MaxReturn -52.3515 +Average/MinReturn -125.999 +Average/NumEpisodes 120 +Average/StdReturn 12.5242 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97087 +GaussianMLPPolicy/KLAfter 0.005551 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.69825e-05 +GaussianMLPPolicy/LossBefore 1.73251e-08 +GaussianMLPPolicy/dLoss 2.69998e-05 +Iteration 56 +MetaTest/Average/AverageDiscountedReturn -69.8162 +MetaTest/Average/AverageReturn -69.8162 +MetaTest/Average/Iteration 56 +MetaTest/Average/MaxReturn -51.7318 +MetaTest/Average/MinReturn -88.2777 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.3392 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -69.8162 +MetaTest/__unnamed_task__/AverageReturn -69.8162 +MetaTest/__unnamed_task__/Iteration 56 +MetaTest/__unnamed_task__/MaxReturn -51.7318 +MetaTest/__unnamed_task__/MinReturn -88.2777 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.3392 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.736e+06 +__unnamed_task__/AverageDiscountedReturn -34.6212 +__unnamed_task__/AverageReturn -70.0492 +__unnamed_task__/Iteration 56 +__unnamed_task__/MaxReturn -52.3515 +__unnamed_task__/MinReturn -125.999 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.5242 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 18:43:35 | [maml_trainer] epoch #57 | Sampling for adapation and meta-testing... +2025-04-04 18:47:27 | [maml_trainer] epoch #57 | Finished meta-testing... +2025-04-04 18:47:27 | [maml_trainer] epoch #57 | Saving snapshot... +2025-04-04 18:47:47 | [maml_trainer] epoch #57 | Saved +2025-04-04 18:47:47 | [maml_trainer] epoch #57 | Time 94111.06 s +2025-04-04 18:47:47 | [maml_trainer] epoch #57 | EpochTime 1661.03 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -35.1296 +Average/AverageReturn -71.9918 +Average/Iteration 57 +Average/MaxReturn -48.91 +Average/MinReturn -136.921 +Average/NumEpisodes 120 +Average/StdReturn 14.3633 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97518 +GaussianMLPPolicy/KLAfter 0.00532968 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.72001e-05 +GaussianMLPPolicy/LossBefore -2.06629e-09 +GaussianMLPPolicy/dLoss 3.71981e-05 +Iteration 57 +MetaTest/Average/AverageDiscountedReturn -68.5407 +MetaTest/Average/AverageReturn -68.5407 +MetaTest/Average/Iteration 57 +MetaTest/Average/MaxReturn -50.7192 +MetaTest/Average/MinReturn -157.52 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 22.0076 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -68.5407 +MetaTest/__unnamed_task__/AverageReturn -68.5407 +MetaTest/__unnamed_task__/Iteration 57 +MetaTest/__unnamed_task__/MaxReturn -50.7192 +MetaTest/__unnamed_task__/MinReturn -157.52 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 22.0076 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.784e+06 +__unnamed_task__/AverageDiscountedReturn -35.1296 +__unnamed_task__/AverageReturn -71.9918 +__unnamed_task__/Iteration 57 +__unnamed_task__/MaxReturn -48.91 +__unnamed_task__/MinReturn -136.921 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.3633 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 19:11:54 | [maml_trainer] epoch #58 | Sampling for adapation and meta-testing... +2025-04-04 19:15:53 | [maml_trainer] epoch #58 | Finished meta-testing... +2025-04-04 19:15:53 | [maml_trainer] epoch #58 | Saving snapshot... +2025-04-04 19:16:13 | [maml_trainer] epoch #58 | Saved +2025-04-04 19:16:13 | [maml_trainer] epoch #58 | Time 95817.81 s +2025-04-04 19:16:13 | [maml_trainer] epoch #58 | EpochTime 1706.75 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.8416 +Average/AverageReturn -68.2187 +Average/Iteration 58 +Average/MaxReturn -47.9124 +Average/MinReturn -150.706 +Average/NumEpisodes 120 +Average/StdReturn 15.3394 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97898 +GaussianMLPPolicy/KLAfter 0.00438835 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.60257e-05 +GaussianMLPPolicy/LossBefore 9.85464e-09 +GaussianMLPPolicy/dLoss -6.60158e-05 +Iteration 58 +MetaTest/Average/AverageDiscountedReturn -66.873 +MetaTest/Average/AverageReturn -66.873 +MetaTest/Average/Iteration 58 +MetaTest/Average/MaxReturn -46.0704 +MetaTest/Average/MinReturn -133.441 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 18.8488 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -66.873 +MetaTest/__unnamed_task__/AverageReturn -66.873 +MetaTest/__unnamed_task__/Iteration 58 +MetaTest/__unnamed_task__/MaxReturn -46.0704 +MetaTest/__unnamed_task__/MinReturn -133.441 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 18.8488 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.832e+06 +__unnamed_task__/AverageDiscountedReturn -33.8416 +__unnamed_task__/AverageReturn -68.2187 +__unnamed_task__/Iteration 58 +__unnamed_task__/MaxReturn -47.9124 +__unnamed_task__/MinReturn -150.706 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.3394 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 19:39:45 | [maml_trainer] epoch #59 | Sampling for adapation and meta-testing... +2025-04-04 19:43:39 | [maml_trainer] epoch #59 | Finished meta-testing... +2025-04-04 19:43:39 | [maml_trainer] epoch #59 | Saving snapshot... +2025-04-04 19:43:59 | [maml_trainer] epoch #59 | Saved +2025-04-04 19:43:59 | [maml_trainer] epoch #59 | Time 97483.36 s +2025-04-04 19:43:59 | [maml_trainer] epoch #59 | EpochTime 1665.54 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.1732 +Average/AverageReturn -69.6874 +Average/Iteration 59 +Average/MaxReturn -49.2629 +Average/MinReturn -144.466 +Average/NumEpisodes 120 +Average/StdReturn 17.8696 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.98203 +GaussianMLPPolicy/KLAfter 0.00541235 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.44214e-05 +GaussianMLPPolicy/LossBefore 8.78175e-09 +GaussianMLPPolicy/dLoss -2.44126e-05 +Iteration 59 +MetaTest/Average/AverageDiscountedReturn -65.5487 +MetaTest/Average/AverageReturn -65.5487 +MetaTest/Average/Iteration 59 +MetaTest/Average/MaxReturn -50.7083 +MetaTest/Average/MinReturn -112.809 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.8204 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -65.5487 +MetaTest/__unnamed_task__/AverageReturn -65.5487 +MetaTest/__unnamed_task__/Iteration 59 +MetaTest/__unnamed_task__/MaxReturn -50.7083 +MetaTest/__unnamed_task__/MinReturn -112.809 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.8204 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.88e+06 +__unnamed_task__/AverageDiscountedReturn -34.1732 +__unnamed_task__/AverageReturn -69.6874 +__unnamed_task__/Iteration 59 +__unnamed_task__/MaxReturn -49.2629 +__unnamed_task__/MinReturn -144.466 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.8696 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 20:07:36 | [maml_trainer] epoch #60 | Sampling for adapation and meta-testing... +2025-04-04 20:11:31 | [maml_trainer] epoch #60 | Finished meta-testing... +2025-04-04 20:11:31 | [maml_trainer] epoch #60 | Saving snapshot... +2025-04-04 20:11:51 | [maml_trainer] epoch #60 | Saved +2025-04-04 20:11:51 | [maml_trainer] epoch #60 | Time 99155.58 s +2025-04-04 20:11:51 | [maml_trainer] epoch #60 | EpochTime 1672.22 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.6438 +Average/AverageReturn -66.9869 +Average/Iteration 60 +Average/MaxReturn -48.1345 +Average/MinReturn -128.144 +Average/NumEpisodes 120 +Average/StdReturn 14.0339 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.98544 +GaussianMLPPolicy/KLAfter 0.00572111 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.71357e-05 +GaussianMLPPolicy/LossBefore 1.14044e-08 +GaussianMLPPolicy/dLoss 4.71471e-05 +Iteration 60 +MetaTest/Average/AverageDiscountedReturn -74.3002 +MetaTest/Average/AverageReturn -74.3002 +MetaTest/Average/Iteration 60 +MetaTest/Average/MaxReturn -49.107 +MetaTest/Average/MinReturn -147.486 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 26.1454 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -74.3002 +MetaTest/__unnamed_task__/AverageReturn -74.3002 +MetaTest/__unnamed_task__/Iteration 60 +MetaTest/__unnamed_task__/MaxReturn -49.107 +MetaTest/__unnamed_task__/MinReturn -147.486 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 26.1454 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.928e+06 +__unnamed_task__/AverageDiscountedReturn -33.6438 +__unnamed_task__/AverageReturn -66.9869 +__unnamed_task__/Iteration 60 +__unnamed_task__/MaxReturn -48.1345 +__unnamed_task__/MinReturn -128.144 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.0339 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 20:35:25 | [maml_trainer] epoch #61 | Sampling for adapation and meta-testing... +2025-04-04 20:39:19 | [maml_trainer] epoch #61 | Finished meta-testing... +2025-04-04 20:39:19 | [maml_trainer] epoch #61 | Saving snapshot... +2025-04-04 20:39:39 | [maml_trainer] epoch #61 | Saved +2025-04-04 20:39:39 | [maml_trainer] epoch #61 | Time 100823.31 s +2025-04-04 20:39:39 | [maml_trainer] epoch #61 | EpochTime 1667.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.9739 +Average/AverageReturn -68.4003 +Average/Iteration 61 +Average/MaxReturn -50.6182 +Average/MinReturn -154.961 +Average/NumEpisodes 120 +Average/StdReturn 17.6178 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.98834 +GaussianMLPPolicy/KLAfter 0.00617085 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.26415e-05 +GaussianMLPPolicy/LossBefore 3.23852e-09 +GaussianMLPPolicy/dLoss 6.26447e-05 +Iteration 61 +MetaTest/Average/AverageDiscountedReturn -71.6684 +MetaTest/Average/AverageReturn -71.6684 +MetaTest/Average/Iteration 61 +MetaTest/Average/MaxReturn -46.0098 +MetaTest/Average/MinReturn -148.054 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.2163 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -71.6684 +MetaTest/__unnamed_task__/AverageReturn -71.6684 +MetaTest/__unnamed_task__/Iteration 61 +MetaTest/__unnamed_task__/MaxReturn -46.0098 +MetaTest/__unnamed_task__/MinReturn -148.054 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.2163 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.976e+06 +__unnamed_task__/AverageDiscountedReturn -33.9739 +__unnamed_task__/AverageReturn -68.4003 +__unnamed_task__/Iteration 61 +__unnamed_task__/MaxReturn -50.6182 +__unnamed_task__/MinReturn -154.961 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.6178 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 21:03:20 | [maml_trainer] epoch #62 | Sampling for adapation and meta-testing... +2025-04-04 21:07:16 | [maml_trainer] epoch #62 | Finished meta-testing... +2025-04-04 21:07:16 | [maml_trainer] epoch #62 | Saving snapshot... +2025-04-04 21:07:37 | [maml_trainer] epoch #62 | Saved +2025-04-04 21:07:37 | [maml_trainer] epoch #62 | Time 102501.03 s +2025-04-04 21:07:37 | [maml_trainer] epoch #62 | EpochTime 1677.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.2308 +Average/AverageReturn -67.5738 +Average/Iteration 62 +Average/MaxReturn -48.646 +Average/MinReturn -137.368 +Average/NumEpisodes 120 +Average/StdReturn 16.241 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99146 +GaussianMLPPolicy/KLAfter 0.00690271 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.7777e-06 +GaussianMLPPolicy/LossBefore 2.78155e-09 +GaussianMLPPolicy/dLoss -5.77492e-06 +Iteration 62 +MetaTest/Average/AverageDiscountedReturn -66.4695 +MetaTest/Average/AverageReturn -66.4695 +MetaTest/Average/Iteration 62 +MetaTest/Average/MaxReturn -47.247 +MetaTest/Average/MinReturn -110.701 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.293 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -66.4695 +MetaTest/__unnamed_task__/AverageReturn -66.4695 +MetaTest/__unnamed_task__/Iteration 62 +MetaTest/__unnamed_task__/MaxReturn -47.247 +MetaTest/__unnamed_task__/MinReturn -110.701 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.293 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.024e+06 +__unnamed_task__/AverageDiscountedReturn -34.2308 +__unnamed_task__/AverageReturn -67.5738 +__unnamed_task__/Iteration 62 +__unnamed_task__/MaxReturn -48.646 +__unnamed_task__/MinReturn -137.368 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.241 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 21:31:25 | [maml_trainer] epoch #63 | Sampling for adapation and meta-testing... +2025-04-04 21:35:21 | [maml_trainer] epoch #63 | Finished meta-testing... +2025-04-04 21:35:21 | [maml_trainer] epoch #63 | Saving snapshot... +2025-04-04 21:35:42 | [maml_trainer] epoch #63 | Saved +2025-04-04 21:35:42 | [maml_trainer] epoch #63 | Time 104186.00 s +2025-04-04 21:35:42 | [maml_trainer] epoch #63 | EpochTime 1684.97 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.1882 +Average/AverageReturn -63.0262 +Average/Iteration 63 +Average/MaxReturn -48.5005 +Average/MinReturn -108.673 +Average/NumEpisodes 120 +Average/StdReturn 9.81466 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99412 +GaussianMLPPolicy/KLAfter 0.00584469 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.75662e-05 +GaussianMLPPolicy/LossBefore -5.48363e-09 +GaussianMLPPolicy/dLoss 1.75607e-05 +Iteration 63 +MetaTest/Average/AverageDiscountedReturn -60.4493 +MetaTest/Average/AverageReturn -60.4493 +MetaTest/Average/Iteration 63 +MetaTest/Average/MaxReturn -50.3962 +MetaTest/Average/MinReturn -74.8365 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.99921 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.4493 +MetaTest/__unnamed_task__/AverageReturn -60.4493 +MetaTest/__unnamed_task__/Iteration 63 +MetaTest/__unnamed_task__/MaxReturn -50.3962 +MetaTest/__unnamed_task__/MinReturn -74.8365 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.99921 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.072e+06 +__unnamed_task__/AverageDiscountedReturn -33.1882 +__unnamed_task__/AverageReturn -63.0262 +__unnamed_task__/Iteration 63 +__unnamed_task__/MaxReturn -48.5005 +__unnamed_task__/MinReturn -108.673 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.81466 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 21:59:28 | [maml_trainer] epoch #64 | Sampling for adapation and meta-testing... +2025-04-04 22:03:22 | [maml_trainer] epoch #64 | Finished meta-testing... +2025-04-04 22:03:22 | [maml_trainer] epoch #64 | Saving snapshot... +2025-04-04 22:03:42 | [maml_trainer] epoch #64 | Saved +2025-04-04 22:03:42 | [maml_trainer] epoch #64 | Time 105866.16 s +2025-04-04 22:03:42 | [maml_trainer] epoch #64 | EpochTime 1680.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.4542 +Average/AverageReturn -64.4139 +Average/Iteration 64 +Average/MaxReturn -50.1815 +Average/MinReturn -156.718 +Average/NumEpisodes 120 +Average/StdReturn 15.5578 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99703 +GaussianMLPPolicy/KLAfter 0.0066887 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.83245e-05 +GaussianMLPPolicy/LossBefore 1.09275e-08 +GaussianMLPPolicy/dLoss 2.83354e-05 +Iteration 64 +MetaTest/Average/AverageDiscountedReturn -60.9685 +MetaTest/Average/AverageReturn -60.9685 +MetaTest/Average/Iteration 64 +MetaTest/Average/MaxReturn -50.2794 +MetaTest/Average/MinReturn -69.4478 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.18559 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.9685 +MetaTest/__unnamed_task__/AverageReturn -60.9685 +MetaTest/__unnamed_task__/Iteration 64 +MetaTest/__unnamed_task__/MaxReturn -50.2794 +MetaTest/__unnamed_task__/MinReturn -69.4478 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.18559 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.12e+06 +__unnamed_task__/AverageDiscountedReturn -33.4542 +__unnamed_task__/AverageReturn -64.4139 +__unnamed_task__/Iteration 64 +__unnamed_task__/MaxReturn -50.1815 +__unnamed_task__/MinReturn -156.718 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.5578 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 22:27:08 | [maml_trainer] epoch #65 | Sampling for adapation and meta-testing... +2025-04-04 22:31:01 | [maml_trainer] epoch #65 | Finished meta-testing... +2025-04-04 22:31:01 | [maml_trainer] epoch #65 | Saving snapshot... +2025-04-04 22:31:21 | [maml_trainer] epoch #65 | Saved +2025-04-04 22:31:21 | [maml_trainer] epoch #65 | Time 107525.89 s +2025-04-04 22:31:21 | [maml_trainer] epoch #65 | EpochTime 1659.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.9394 +Average/AverageReturn -62.1037 +Average/Iteration 65 +Average/MaxReturn -45.7031 +Average/MinReturn -157.685 +Average/NumEpisodes 120 +Average/StdReturn 12.0661 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99837 +GaussianMLPPolicy/KLAfter 0.00748525 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.6652e-05 +GaussianMLPPolicy/LossBefore -3.13918e-09 +GaussianMLPPolicy/dLoss 8.66489e-05 +Iteration 65 +MetaTest/Average/AverageDiscountedReturn -59.2136 +MetaTest/Average/AverageReturn -59.2136 +MetaTest/Average/Iteration 65 +MetaTest/Average/MaxReturn -49.3458 +MetaTest/Average/MinReturn -71.11 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.28226 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -59.2136 +MetaTest/__unnamed_task__/AverageReturn -59.2136 +MetaTest/__unnamed_task__/Iteration 65 +MetaTest/__unnamed_task__/MaxReturn -49.3458 +MetaTest/__unnamed_task__/MinReturn -71.11 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.28226 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.168e+06 +__unnamed_task__/AverageDiscountedReturn -32.9394 +__unnamed_task__/AverageReturn -62.1037 +__unnamed_task__/Iteration 65 +__unnamed_task__/MaxReturn -45.7031 +__unnamed_task__/MinReturn -157.685 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.0661 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 22:54:41 | [maml_trainer] epoch #66 | Sampling for adapation and meta-testing... +2025-04-04 22:58:33 | [maml_trainer] epoch #66 | Finished meta-testing... +2025-04-04 22:58:34 | [maml_trainer] epoch #66 | Saving snapshot... +2025-04-04 22:58:54 | [maml_trainer] epoch #66 | Saved +2025-04-04 22:58:54 | [maml_trainer] epoch #66 | Time 109178.06 s +2025-04-04 22:58:54 | [maml_trainer] epoch #66 | EpochTime 1652.17 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.6559 +Average/AverageReturn -61.5584 +Average/Iteration 66 +Average/MaxReturn -47.222 +Average/MinReturn -131.475 +Average/NumEpisodes 120 +Average/StdReturn 13.788 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99925 +GaussianMLPPolicy/KLAfter 0.00683781 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.41906e-05 +GaussianMLPPolicy/LossBefore 9.41753e-09 +GaussianMLPPolicy/dLoss -8.41812e-05 +Iteration 66 +MetaTest/Average/AverageDiscountedReturn -57.1593 +MetaTest/Average/AverageReturn -57.1593 +MetaTest/Average/Iteration 66 +MetaTest/Average/MaxReturn -47.7196 +MetaTest/Average/MinReturn -68.4743 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.48636 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1593 +MetaTest/__unnamed_task__/AverageReturn -57.1593 +MetaTest/__unnamed_task__/Iteration 66 +MetaTest/__unnamed_task__/MaxReturn -47.7196 +MetaTest/__unnamed_task__/MinReturn -68.4743 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.48636 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.216e+06 +__unnamed_task__/AverageDiscountedReturn -32.6559 +__unnamed_task__/AverageReturn -61.5584 +__unnamed_task__/Iteration 66 +__unnamed_task__/MaxReturn -47.222 +__unnamed_task__/MinReturn -131.475 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.788 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-04 23:21:51 | [maml_trainer] epoch #67 | Sampling for adapation and meta-testing... +2025-04-04 23:25:45 | [maml_trainer] epoch #67 | Finished meta-testing... +2025-04-04 23:25:45 | [maml_trainer] epoch #67 | Saving snapshot... +2025-04-04 23:26:06 | [maml_trainer] epoch #67 | Saved +2025-04-04 23:26:06 | [maml_trainer] epoch #67 | Time 110810.35 s +2025-04-04 23:26:06 | [maml_trainer] epoch #67 | EpochTime 1632.28 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.3946 +Average/AverageReturn -58.8171 +Average/Iteration 67 +Average/MaxReturn -47.1557 +Average/MinReturn -82.5453 +Average/NumEpisodes 120 +Average/StdReturn 5.77513 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99892 +GaussianMLPPolicy/KLAfter 0.00683179 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000102886 +GaussianMLPPolicy/LossBefore 4.76837e-09 +GaussianMLPPolicy/dLoss 0.000102891 +Iteration 67 +MetaTest/Average/AverageDiscountedReturn -57.8278 +MetaTest/Average/AverageReturn -57.8278 +MetaTest/Average/Iteration 67 +MetaTest/Average/MaxReturn -48.8225 +MetaTest/Average/MinReturn -67.5294 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.55107 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.8278 +MetaTest/__unnamed_task__/AverageReturn -57.8278 +MetaTest/__unnamed_task__/Iteration 67 +MetaTest/__unnamed_task__/MaxReturn -48.8225 +MetaTest/__unnamed_task__/MinReturn -67.5294 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.55107 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.264e+06 +__unnamed_task__/AverageDiscountedReturn -32.3946 +__unnamed_task__/AverageReturn -58.8171 +__unnamed_task__/Iteration 67 +__unnamed_task__/MaxReturn -47.1557 +__unnamed_task__/MinReturn -82.5453 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.77513 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-04 23:49:23 | [maml_trainer] epoch #68 | Sampling for adapation and meta-testing... +2025-04-04 23:53:17 | [maml_trainer] epoch #68 | Finished meta-testing... +2025-04-04 23:53:17 | [maml_trainer] epoch #68 | Saving snapshot... +2025-04-04 23:53:37 | [maml_trainer] epoch #68 | Saved +2025-04-04 23:53:37 | [maml_trainer] epoch #68 | Time 112461.82 s +2025-04-04 23:53:37 | [maml_trainer] epoch #68 | EpochTime 1651.46 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.3726 +Average/AverageReturn -58.5267 +Average/Iteration 68 +Average/MaxReturn -47.0963 +Average/MinReturn -80.6368 +Average/NumEpisodes 120 +Average/StdReturn 5.87898 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99826 +GaussianMLPPolicy/KLAfter 0.00595331 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.37019e-05 +GaussianMLPPolicy/LossBefore 1.33912e-08 +GaussianMLPPolicy/dLoss 1.37153e-05 +Iteration 68 +MetaTest/Average/AverageDiscountedReturn -57.6583 +MetaTest/Average/AverageReturn -57.6583 +MetaTest/Average/Iteration 68 +MetaTest/Average/MaxReturn -49.5115 +MetaTest/Average/MinReturn -88.6595 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.02781 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.6583 +MetaTest/__unnamed_task__/AverageReturn -57.6583 +MetaTest/__unnamed_task__/Iteration 68 +MetaTest/__unnamed_task__/MaxReturn -49.5115 +MetaTest/__unnamed_task__/MinReturn -88.6595 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.02781 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.312e+06 +__unnamed_task__/AverageDiscountedReturn -32.3726 +__unnamed_task__/AverageReturn -58.5267 +__unnamed_task__/Iteration 68 +__unnamed_task__/MaxReturn -47.0963 +__unnamed_task__/MinReturn -80.6368 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.87898 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 00:16:58 | [maml_trainer] epoch #69 | Sampling for adapation and meta-testing... +2025-04-05 00:20:49 | [maml_trainer] epoch #69 | Finished meta-testing... +2025-04-05 00:20:49 | [maml_trainer] epoch #69 | Saving snapshot... +2025-04-05 00:21:09 | [maml_trainer] epoch #69 | Saved +2025-04-05 00:21:09 | [maml_trainer] epoch #69 | Time 114113.54 s +2025-04-05 00:21:09 | [maml_trainer] epoch #69 | EpochTime 1651.72 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.3983 +Average/AverageReturn -58.4798 +Average/Iteration 69 +Average/MaxReturn -47.4579 +Average/MinReturn -74.4689 +Average/NumEpisodes 120 +Average/StdReturn 5.46807 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99622 +GaussianMLPPolicy/KLAfter 0.00645062 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.81e-05 +GaussianMLPPolicy/LossBefore 2.14577e-09 +GaussianMLPPolicy/dLoss -1.80978e-05 +Iteration 69 +MetaTest/Average/AverageDiscountedReturn -56.5389 +MetaTest/Average/AverageReturn -56.5389 +MetaTest/Average/Iteration 69 +MetaTest/Average/MaxReturn -49.9342 +MetaTest/Average/MinReturn -65.6988 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.82455 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.5389 +MetaTest/__unnamed_task__/AverageReturn -56.5389 +MetaTest/__unnamed_task__/Iteration 69 +MetaTest/__unnamed_task__/MaxReturn -49.9342 +MetaTest/__unnamed_task__/MinReturn -65.6988 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.82455 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.36e+06 +__unnamed_task__/AverageDiscountedReturn -32.3983 +__unnamed_task__/AverageReturn -58.4798 +__unnamed_task__/Iteration 69 +__unnamed_task__/MaxReturn -47.4579 +__unnamed_task__/MinReturn -74.4689 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.46807 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 00:44:06 | [maml_trainer] epoch #70 | Sampling for adapation and meta-testing... +2025-04-05 00:48:02 | [maml_trainer] epoch #70 | Finished meta-testing... +2025-04-05 00:48:02 | [maml_trainer] epoch #70 | Saving snapshot... +2025-04-05 00:48:23 | [maml_trainer] epoch #70 | Saved +2025-04-05 00:48:23 | [maml_trainer] epoch #70 | Time 115747.15 s +2025-04-05 00:48:23 | [maml_trainer] epoch #70 | EpochTime 1633.61 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.2276 +Average/AverageReturn -58.0794 +Average/Iteration 70 +Average/MaxReturn -47.3674 +Average/MinReturn -76.3788 +Average/NumEpisodes 120 +Average/StdReturn 5.69181 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.99262 +GaussianMLPPolicy/KLAfter 0.00811791 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.00014378 +GaussianMLPPolicy/LossBefore -1.54972e-09 +GaussianMLPPolicy/dLoss -0.000143782 +Iteration 70 +MetaTest/Average/AverageDiscountedReturn -57.9636 +MetaTest/Average/AverageReturn -57.9636 +MetaTest/Average/Iteration 70 +MetaTest/Average/MaxReturn -46.0649 +MetaTest/Average/MinReturn -80.1261 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.61944 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.9636 +MetaTest/__unnamed_task__/AverageReturn -57.9636 +MetaTest/__unnamed_task__/Iteration 70 +MetaTest/__unnamed_task__/MaxReturn -46.0649 +MetaTest/__unnamed_task__/MinReturn -80.1261 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.61944 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.408e+06 +__unnamed_task__/AverageDiscountedReturn -32.2276 +__unnamed_task__/AverageReturn -58.0794 +__unnamed_task__/Iteration 70 +__unnamed_task__/MaxReturn -47.3674 +__unnamed_task__/MinReturn -76.3788 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.69181 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 01:11:52 | [maml_trainer] epoch #71 | Sampling for adapation and meta-testing... +2025-04-05 01:15:40 | [maml_trainer] epoch #71 | Finished meta-testing... +2025-04-05 01:15:40 | [maml_trainer] epoch #71 | Saving snapshot... +2025-04-05 01:16:00 | [maml_trainer] epoch #71 | Saved +2025-04-05 01:16:00 | [maml_trainer] epoch #71 | Time 117404.48 s +2025-04-05 01:16:00 | [maml_trainer] epoch #71 | EpochTime 1657.33 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.3809 +Average/AverageReturn -58.6185 +Average/Iteration 71 +Average/MaxReturn -48.1933 +Average/MinReturn -78.7347 +Average/NumEpisodes 120 +Average/StdReturn 5.84311 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.98813 +GaussianMLPPolicy/KLAfter 0.007888 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.0076e-05 +GaussianMLPPolicy/LossBefore 1.24375e-08 +GaussianMLPPolicy/dLoss 8.00885e-05 +Iteration 71 +MetaTest/Average/AverageDiscountedReturn -59.6236 +MetaTest/Average/AverageReturn -59.6236 +MetaTest/Average/Iteration 71 +MetaTest/Average/MaxReturn -49.5389 +MetaTest/Average/MinReturn -72.4505 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.50315 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -59.6236 +MetaTest/__unnamed_task__/AverageReturn -59.6236 +MetaTest/__unnamed_task__/Iteration 71 +MetaTest/__unnamed_task__/MaxReturn -49.5389 +MetaTest/__unnamed_task__/MinReturn -72.4505 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.50315 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.456e+06 +__unnamed_task__/AverageDiscountedReturn -32.3809 +__unnamed_task__/AverageReturn -58.6185 +__unnamed_task__/Iteration 71 +__unnamed_task__/MaxReturn -48.1933 +__unnamed_task__/MinReturn -78.7347 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.84311 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 01:39:13 | [maml_trainer] epoch #72 | Sampling for adapation and meta-testing... +2025-04-05 01:43:05 | [maml_trainer] epoch #72 | Finished meta-testing... +2025-04-05 01:43:05 | [maml_trainer] epoch #72 | Saving snapshot... +2025-04-05 01:43:25 | [maml_trainer] epoch #72 | Saved +2025-04-05 01:43:25 | [maml_trainer] epoch #72 | Time 119049.89 s +2025-04-05 01:43:25 | [maml_trainer] epoch #72 | EpochTime 1645.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -32.6999 +Average/AverageReturn -59.7331 +Average/Iteration 72 +Average/MaxReturn -48.0436 +Average/MinReturn -87.3308 +Average/NumEpisodes 120 +Average/StdReturn 7.2699 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.98419 +GaussianMLPPolicy/KLAfter 0.00680742 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.50123e-05 +GaussianMLPPolicy/LossBefore -2.66234e-09 +GaussianMLPPolicy/dLoss 1.50096e-05 +Iteration 72 +MetaTest/Average/AverageDiscountedReturn -56.1916 +MetaTest/Average/AverageReturn -56.1916 +MetaTest/Average/Iteration 72 +MetaTest/Average/MaxReturn -48.5814 +MetaTest/Average/MinReturn -75.8151 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.91383 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.1916 +MetaTest/__unnamed_task__/AverageReturn -56.1916 +MetaTest/__unnamed_task__/Iteration 72 +MetaTest/__unnamed_task__/MaxReturn -48.5814 +MetaTest/__unnamed_task__/MinReturn -75.8151 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.91383 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.504e+06 +__unnamed_task__/AverageDiscountedReturn -32.6999 +__unnamed_task__/AverageReturn -59.7331 +__unnamed_task__/Iteration 72 +__unnamed_task__/MaxReturn -48.0436 +__unnamed_task__/MinReturn -87.3308 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.2699 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 02:06:39 | [maml_trainer] epoch #73 | Sampling for adapation and meta-testing... +2025-04-05 02:10:29 | [maml_trainer] epoch #73 | Finished meta-testing... +2025-04-05 02:10:29 | [maml_trainer] epoch #73 | Saving snapshot... +2025-04-05 02:10:49 | [maml_trainer] epoch #73 | Saved +2025-04-05 02:10:49 | [maml_trainer] epoch #73 | Time 120693.72 s +2025-04-05 02:10:49 | [maml_trainer] epoch #73 | EpochTime 1643.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -31.9527 +Average/AverageReturn -57.8923 +Average/Iteration 73 +Average/MaxReturn -46.8038 +Average/MinReturn -81.1373 +Average/NumEpisodes 120 +Average/StdReturn 6.93702 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9802 +GaussianMLPPolicy/KLAfter 0.00916397 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000172868 +GaussianMLPPolicy/LossBefore -4.05312e-09 +GaussianMLPPolicy/dLoss 0.000172864 +Iteration 73 +MetaTest/Average/AverageDiscountedReturn -62.6487 +MetaTest/Average/AverageReturn -62.6487 +MetaTest/Average/Iteration 73 +MetaTest/Average/MaxReturn -51.4459 +MetaTest/Average/MinReturn -93.4157 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.04842 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -62.6487 +MetaTest/__unnamed_task__/AverageReturn -62.6487 +MetaTest/__unnamed_task__/Iteration 73 +MetaTest/__unnamed_task__/MaxReturn -51.4459 +MetaTest/__unnamed_task__/MinReturn -93.4157 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.04842 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.552e+06 +__unnamed_task__/AverageDiscountedReturn -31.9527 +__unnamed_task__/AverageReturn -57.8923 +__unnamed_task__/Iteration 73 +__unnamed_task__/MaxReturn -46.8038 +__unnamed_task__/MinReturn -81.1373 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.93702 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 02:33:54 | [maml_trainer] epoch #74 | Sampling for adapation and meta-testing... +2025-04-05 02:37:41 | [maml_trainer] epoch #74 | Finished meta-testing... +2025-04-05 02:37:41 | [maml_trainer] epoch #74 | Saving snapshot... +2025-04-05 02:38:01 | [maml_trainer] epoch #74 | Saved +2025-04-05 02:38:01 | [maml_trainer] epoch #74 | Time 122325.95 s +2025-04-05 02:38:01 | [maml_trainer] epoch #74 | EpochTime 1632.23 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.11 +Average/AverageReturn -59.021 +Average/Iteration 74 +Average/MaxReturn -44.4808 +Average/MinReturn -147.59 +Average/NumEpisodes 120 +Average/StdReturn 10.6454 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97728 +GaussianMLPPolicy/KLAfter 0.0081299 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.19652e-05 +GaussianMLPPolicy/LossBefore -4.60943e-09 +GaussianMLPPolicy/dLoss 8.19606e-05 +Iteration 74 +MetaTest/Average/AverageDiscountedReturn -56.6359 +MetaTest/Average/AverageReturn -56.6359 +MetaTest/Average/Iteration 74 +MetaTest/Average/MaxReturn -47.596 +MetaTest/Average/MinReturn -65.3359 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.99441 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.6359 +MetaTest/__unnamed_task__/AverageReturn -56.6359 +MetaTest/__unnamed_task__/Iteration 74 +MetaTest/__unnamed_task__/MaxReturn -47.596 +MetaTest/__unnamed_task__/MinReturn -65.3359 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.99441 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.6e+06 +__unnamed_task__/AverageDiscountedReturn -32.11 +__unnamed_task__/AverageReturn -59.021 +__unnamed_task__/Iteration 74 +__unnamed_task__/MaxReturn -44.4808 +__unnamed_task__/MinReturn -147.59 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.6454 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 03:01:07 | [maml_trainer] epoch #75 | Sampling for adapation and meta-testing... +2025-04-05 03:04:59 | [maml_trainer] epoch #75 | Finished meta-testing... +2025-04-05 03:04:59 | [maml_trainer] epoch #75 | Saving snapshot... +2025-04-05 03:05:19 | [maml_trainer] epoch #75 | Saved +2025-04-05 03:05:19 | [maml_trainer] epoch #75 | Time 123963.85 s +2025-04-05 03:05:19 | [maml_trainer] epoch #75 | EpochTime 1637.89 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.3605 +Average/AverageReturn -59.8418 +Average/Iteration 75 +Average/MaxReturn -46.1727 +Average/MinReturn -126.267 +Average/NumEpisodes 120 +Average/StdReturn 10.8108 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97521 +GaussianMLPPolicy/KLAfter 0.00648716 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.08444e-06 +GaussianMLPPolicy/LossBefore -8.38439e-09 +GaussianMLPPolicy/dLoss 5.07605e-06 +Iteration 75 +MetaTest/Average/AverageDiscountedReturn -53.9219 +MetaTest/Average/AverageReturn -53.9219 +MetaTest/Average/Iteration 75 +MetaTest/Average/MaxReturn -42.9947 +MetaTest/Average/MinReturn -76.4795 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.60454 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.9219 +MetaTest/__unnamed_task__/AverageReturn -53.9219 +MetaTest/__unnamed_task__/Iteration 75 +MetaTest/__unnamed_task__/MaxReturn -42.9947 +MetaTest/__unnamed_task__/MinReturn -76.4795 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.60454 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.648e+06 +__unnamed_task__/AverageDiscountedReturn -32.3605 +__unnamed_task__/AverageReturn -59.8418 +__unnamed_task__/Iteration 75 +__unnamed_task__/MaxReturn -46.1727 +__unnamed_task__/MinReturn -126.267 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.8108 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 03:28:37 | [maml_trainer] epoch #76 | Sampling for adapation and meta-testing... +2025-04-05 03:32:29 | [maml_trainer] epoch #76 | Finished meta-testing... +2025-04-05 03:32:29 | [maml_trainer] epoch #76 | Saving snapshot... +2025-04-05 03:32:49 | [maml_trainer] epoch #76 | Saved +2025-04-05 03:32:49 | [maml_trainer] epoch #76 | Time 125613.74 s +2025-04-05 03:32:49 | [maml_trainer] epoch #76 | EpochTime 1649.89 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -31.4404 +Average/AverageReturn -57.1847 +Average/Iteration 76 +Average/MaxReturn -46.4346 +Average/MinReturn -86.6627 +Average/NumEpisodes 120 +Average/StdReturn 6.99649 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97216 +GaussianMLPPolicy/KLAfter 0.00489162 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.64641e-05 +GaussianMLPPolicy/LossBefore -3.69549e-09 +GaussianMLPPolicy/dLoss 4.64604e-05 +Iteration 76 +MetaTest/Average/AverageDiscountedReturn -55.1882 +MetaTest/Average/AverageReturn -55.1882 +MetaTest/Average/Iteration 76 +MetaTest/Average/MaxReturn -46.5544 +MetaTest/Average/MinReturn -74.1244 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.10401 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.1882 +MetaTest/__unnamed_task__/AverageReturn -55.1882 +MetaTest/__unnamed_task__/Iteration 76 +MetaTest/__unnamed_task__/MaxReturn -46.5544 +MetaTest/__unnamed_task__/MinReturn -74.1244 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.10401 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.696e+06 +__unnamed_task__/AverageDiscountedReturn -31.4404 +__unnamed_task__/AverageReturn -57.1847 +__unnamed_task__/Iteration 76 +__unnamed_task__/MaxReturn -46.4346 +__unnamed_task__/MinReturn -86.6627 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.99649 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 03:56:05 | [maml_trainer] epoch #77 | Sampling for adapation and meta-testing... +2025-04-05 04:00:00 | [maml_trainer] epoch #77 | Finished meta-testing... +2025-04-05 04:00:00 | [maml_trainer] epoch #77 | Saving snapshot... +2025-04-05 04:00:20 | [maml_trainer] epoch #77 | Saved +2025-04-05 04:00:20 | [maml_trainer] epoch #77 | Time 127264.63 s +2025-04-05 04:00:20 | [maml_trainer] epoch #77 | EpochTime 1650.88 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.4366 +Average/AverageReturn -57.8687 +Average/Iteration 77 +Average/MaxReturn -44.1332 +Average/MinReturn -110.901 +Average/NumEpisodes 120 +Average/StdReturn 9.08424 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.97038 +GaussianMLPPolicy/KLAfter 0.00534654 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.33461e-05 +GaussianMLPPolicy/LossBefore -1.00533e-08 +GaussianMLPPolicy/dLoss -3.33562e-05 +Iteration 77 +MetaTest/Average/AverageDiscountedReturn -59.2099 +MetaTest/Average/AverageReturn -59.2099 +MetaTest/Average/Iteration 77 +MetaTest/Average/MaxReturn -46.6451 +MetaTest/Average/MinReturn -79.7074 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.14225 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -59.2099 +MetaTest/__unnamed_task__/AverageReturn -59.2099 +MetaTest/__unnamed_task__/Iteration 77 +MetaTest/__unnamed_task__/MaxReturn -46.6451 +MetaTest/__unnamed_task__/MinReturn -79.7074 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.14225 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.744e+06 +__unnamed_task__/AverageDiscountedReturn -31.4366 +__unnamed_task__/AverageReturn -57.8687 +__unnamed_task__/Iteration 77 +__unnamed_task__/MaxReturn -44.1332 +__unnamed_task__/MinReturn -110.901 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.08424 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 04:23:33 | [maml_trainer] epoch #78 | Sampling for adapation and meta-testing... +2025-04-05 04:27:23 | [maml_trainer] epoch #78 | Finished meta-testing... +2025-04-05 04:27:23 | [maml_trainer] epoch #78 | Saving snapshot... +2025-04-05 04:27:44 | [maml_trainer] epoch #78 | Saved +2025-04-05 04:27:44 | [maml_trainer] epoch #78 | Time 128908.82 s +2025-04-05 04:27:44 | [maml_trainer] epoch #78 | EpochTime 1644.18 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.5132 +Average/AverageReturn -58.043 +Average/Iteration 78 +Average/MaxReturn -45.7811 +Average/MinReturn -106.196 +Average/NumEpisodes 120 +Average/StdReturn 9.97133 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9691 +GaussianMLPPolicy/KLAfter 0.0048728 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000121232 +GaussianMLPPolicy/LossBefore -1.11262e-09 +GaussianMLPPolicy/dLoss -0.000121233 +Iteration 78 +MetaTest/Average/AverageDiscountedReturn -60.8125 +MetaTest/Average/AverageReturn -60.8125 +MetaTest/Average/Iteration 78 +MetaTest/Average/MaxReturn -47.0598 +MetaTest/Average/MinReturn -77.716 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.551 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.8125 +MetaTest/__unnamed_task__/AverageReturn -60.8125 +MetaTest/__unnamed_task__/Iteration 78 +MetaTest/__unnamed_task__/MaxReturn -47.0598 +MetaTest/__unnamed_task__/MinReturn -77.716 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.551 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.792e+06 +__unnamed_task__/AverageDiscountedReturn -31.5132 +__unnamed_task__/AverageReturn -58.043 +__unnamed_task__/Iteration 78 +__unnamed_task__/MaxReturn -45.7811 +__unnamed_task__/MinReturn -106.196 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.97133 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 04:51:06 | [maml_trainer] epoch #79 | Sampling for adapation and meta-testing... +2025-04-05 04:54:53 | [maml_trainer] epoch #79 | Finished meta-testing... +2025-04-05 04:54:53 | [maml_trainer] epoch #79 | Saving snapshot... +2025-04-05 04:55:13 | [maml_trainer] epoch #79 | Saved +2025-04-05 04:55:13 | [maml_trainer] epoch #79 | Time 130557.68 s +2025-04-05 04:55:13 | [maml_trainer] epoch #79 | EpochTime 1648.86 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -31.5618 +Average/AverageReturn -58.9887 +Average/Iteration 79 +Average/MaxReturn -43.5847 +Average/MinReturn -83.9473 +Average/NumEpisodes 120 +Average/StdReturn 8.95949 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96829 +GaussianMLPPolicy/KLAfter 0.00440186 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.0479e-05 +GaussianMLPPolicy/LossBefore -3.09944e-09 +GaussianMLPPolicy/dLoss 8.04759e-05 +Iteration 79 +MetaTest/Average/AverageDiscountedReturn -61.61 +MetaTest/Average/AverageReturn -61.61 +MetaTest/Average/Iteration 79 +MetaTest/Average/MaxReturn -46.1126 +MetaTest/Average/MinReturn -77.4507 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.22353 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -61.61 +MetaTest/__unnamed_task__/AverageReturn -61.61 +MetaTest/__unnamed_task__/Iteration 79 +MetaTest/__unnamed_task__/MaxReturn -46.1126 +MetaTest/__unnamed_task__/MinReturn -77.4507 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.22353 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.84e+06 +__unnamed_task__/AverageDiscountedReturn -31.5618 +__unnamed_task__/AverageReturn -58.9887 +__unnamed_task__/Iteration 79 +__unnamed_task__/MaxReturn -43.5847 +__unnamed_task__/MinReturn -83.9473 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.95949 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 05:18:08 | [maml_trainer] epoch #80 | Sampling for adapation and meta-testing... +2025-04-05 05:22:04 | [maml_trainer] epoch #80 | Finished meta-testing... +2025-04-05 05:22:04 | [maml_trainer] epoch #80 | Saving snapshot... +2025-04-05 05:22:25 | [maml_trainer] epoch #80 | Saved +2025-04-05 05:22:25 | [maml_trainer] epoch #80 | Time 132189.18 s +2025-04-05 05:22:25 | [maml_trainer] epoch #80 | EpochTime 1631.50 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.2219 +Average/AverageReturn -61.9006 +Average/Iteration 80 +Average/MaxReturn -46.1213 +Average/MinReturn -141.717 +Average/NumEpisodes 120 +Average/StdReturn 12.0617 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96768 +GaussianMLPPolicy/KLAfter 0.00356178 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.47273e-05 +GaussianMLPPolicy/LossBefore -1.19209e-09 +GaussianMLPPolicy/dLoss -1.47285e-05 +Iteration 80 +MetaTest/Average/AverageDiscountedReturn -70.7409 +MetaTest/Average/AverageReturn -70.7409 +MetaTest/Average/Iteration 80 +MetaTest/Average/MaxReturn -49.554 +MetaTest/Average/MinReturn -168.838 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 28.7082 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -70.7409 +MetaTest/__unnamed_task__/AverageReturn -70.7409 +MetaTest/__unnamed_task__/Iteration 80 +MetaTest/__unnamed_task__/MaxReturn -49.554 +MetaTest/__unnamed_task__/MinReturn -168.838 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 28.7082 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.888e+06 +__unnamed_task__/AverageDiscountedReturn -32.2219 +__unnamed_task__/AverageReturn -61.9006 +__unnamed_task__/Iteration 80 +__unnamed_task__/MaxReturn -46.1213 +__unnamed_task__/MinReturn -141.717 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.0617 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 05:45:28 | [maml_trainer] epoch #81 | Sampling for adapation and meta-testing... +2025-04-05 05:49:19 | [maml_trainer] epoch #81 | Finished meta-testing... +2025-04-05 05:49:19 | [maml_trainer] epoch #81 | Saving snapshot... +2025-04-05 05:49:40 | [maml_trainer] epoch #81 | Saved +2025-04-05 05:49:40 | [maml_trainer] epoch #81 | Time 133824.11 s +2025-04-05 05:49:40 | [maml_trainer] epoch #81 | EpochTime 1634.93 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.1801 +Average/AverageReturn -62.0036 +Average/Iteration 81 +Average/MaxReturn -45.4871 +Average/MinReturn -132.866 +Average/NumEpisodes 120 +Average/StdReturn 11.6518 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96698 +GaussianMLPPolicy/KLAfter 0.0051359 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.11683e-05 +GaussianMLPPolicy/LossBefore 7.54992e-09 +GaussianMLPPolicy/dLoss 4.11758e-05 +Iteration 81 +MetaTest/Average/AverageDiscountedReturn -60.4813 +MetaTest/Average/AverageReturn -60.4813 +MetaTest/Average/Iteration 81 +MetaTest/Average/MaxReturn -47.2209 +MetaTest/Average/MinReturn -80.477 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.29384 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.4813 +MetaTest/__unnamed_task__/AverageReturn -60.4813 +MetaTest/__unnamed_task__/Iteration 81 +MetaTest/__unnamed_task__/MaxReturn -47.2209 +MetaTest/__unnamed_task__/MinReturn -80.477 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.29384 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.936e+06 +__unnamed_task__/AverageDiscountedReturn -32.1801 +__unnamed_task__/AverageReturn -62.0036 +__unnamed_task__/Iteration 81 +__unnamed_task__/MaxReturn -45.4871 +__unnamed_task__/MinReturn -132.866 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.6518 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 06:12:56 | [maml_trainer] epoch #82 | Sampling for adapation and meta-testing... +2025-04-05 06:16:48 | [maml_trainer] epoch #82 | Finished meta-testing... +2025-04-05 06:16:48 | [maml_trainer] epoch #82 | Saving snapshot... +2025-04-05 06:17:09 | [maml_trainer] epoch #82 | Saved +2025-04-05 06:17:09 | [maml_trainer] epoch #82 | Time 135473.14 s +2025-04-05 06:17:09 | [maml_trainer] epoch #82 | EpochTime 1649.03 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.2624 +Average/AverageReturn -63.2878 +Average/Iteration 82 +Average/MaxReturn -43.1829 +Average/MinReturn -200.007 +Average/NumEpisodes 120 +Average/StdReturn 17.4658 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96537 +GaussianMLPPolicy/KLAfter 0.00317222 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.65565e-05 +GaussianMLPPolicy/LossBefore 1.39475e-08 +GaussianMLPPolicy/dLoss 8.65705e-05 +Iteration 82 +MetaTest/Average/AverageDiscountedReturn -59.7759 +MetaTest/Average/AverageReturn -59.7759 +MetaTest/Average/Iteration 82 +MetaTest/Average/MaxReturn -46.4403 +MetaTest/Average/MinReturn -80.7 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.116 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -59.7759 +MetaTest/__unnamed_task__/AverageReturn -59.7759 +MetaTest/__unnamed_task__/Iteration 82 +MetaTest/__unnamed_task__/MaxReturn -46.4403 +MetaTest/__unnamed_task__/MinReturn -80.7 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.116 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 3.984e+06 +__unnamed_task__/AverageDiscountedReturn -32.2624 +__unnamed_task__/AverageReturn -63.2878 +__unnamed_task__/Iteration 82 +__unnamed_task__/MaxReturn -43.1829 +__unnamed_task__/MinReturn -200.007 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.4658 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 06:40:18 | [maml_trainer] epoch #83 | Sampling for adapation and meta-testing... +2025-04-05 06:44:05 | [maml_trainer] epoch #83 | Finished meta-testing... +2025-04-05 06:44:05 | [maml_trainer] epoch #83 | Saving snapshot... +2025-04-05 06:44:26 | [maml_trainer] epoch #83 | Saved +2025-04-05 06:44:26 | [maml_trainer] epoch #83 | Time 137110.32 s +2025-04-05 06:44:26 | [maml_trainer] epoch #83 | EpochTime 1637.17 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.3925 +Average/AverageReturn -63.3221 +Average/Iteration 83 +Average/MaxReturn -44.7495 +Average/MinReturn -138.36 +Average/NumEpisodes 120 +Average/StdReturn 14.2104 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96405 +GaussianMLPPolicy/KLAfter 0.00412848 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.68309e-05 +GaussianMLPPolicy/LossBefore -3.97364e-10 +GaussianMLPPolicy/dLoss 9.68305e-05 +Iteration 83 +MetaTest/Average/AverageDiscountedReturn -64.4062 +MetaTest/Average/AverageReturn -64.4062 +MetaTest/Average/Iteration 83 +MetaTest/Average/MaxReturn -44.5491 +MetaTest/Average/MinReturn -153.627 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 23.4197 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -64.4062 +MetaTest/__unnamed_task__/AverageReturn -64.4062 +MetaTest/__unnamed_task__/Iteration 83 +MetaTest/__unnamed_task__/MaxReturn -44.5491 +MetaTest/__unnamed_task__/MinReturn -153.627 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 23.4197 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.032e+06 +__unnamed_task__/AverageDiscountedReturn -32.3925 +__unnamed_task__/AverageReturn -63.3221 +__unnamed_task__/Iteration 83 +__unnamed_task__/MaxReturn -44.7495 +__unnamed_task__/MinReturn -138.36 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.2104 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 07:07:38 | [maml_trainer] epoch #84 | Sampling for adapation and meta-testing... +2025-04-05 07:11:33 | [maml_trainer] epoch #84 | Finished meta-testing... +2025-04-05 07:11:33 | [maml_trainer] epoch #84 | Saving snapshot... +2025-04-05 07:11:55 | [maml_trainer] epoch #84 | Saved +2025-04-05 07:11:55 | [maml_trainer] epoch #84 | Time 138758.99 s +2025-04-05 07:11:55 | [maml_trainer] epoch #84 | EpochTime 1648.67 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.1109 +Average/AverageReturn -60.337 +Average/Iteration 84 +Average/MaxReturn -43.5316 +Average/MinReturn -172.526 +Average/NumEpisodes 120 +Average/StdReturn 16.5557 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96438 +GaussianMLPPolicy/KLAfter 0.00359852 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.89702e-05 +GaussianMLPPolicy/LossBefore -1.11262e-09 +GaussianMLPPolicy/dLoss -2.89714e-05 +Iteration 84 +MetaTest/Average/AverageDiscountedReturn -60.0777 +MetaTest/Average/AverageReturn -60.0777 +MetaTest/Average/Iteration 84 +MetaTest/Average/MaxReturn -48.4434 +MetaTest/Average/MinReturn -90.6847 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.6443 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.0777 +MetaTest/__unnamed_task__/AverageReturn -60.0777 +MetaTest/__unnamed_task__/Iteration 84 +MetaTest/__unnamed_task__/MaxReturn -48.4434 +MetaTest/__unnamed_task__/MinReturn -90.6847 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.6443 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.08e+06 +__unnamed_task__/AverageDiscountedReturn -31.1109 +__unnamed_task__/AverageReturn -60.337 +__unnamed_task__/Iteration 84 +__unnamed_task__/MaxReturn -43.5316 +__unnamed_task__/MinReturn -172.526 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.5557 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 07:35:19 | [maml_trainer] epoch #85 | Sampling for adapation and meta-testing... +2025-04-05 07:39:09 | [maml_trainer] epoch #85 | Finished meta-testing... +2025-04-05 07:39:09 | [maml_trainer] epoch #85 | Saving snapshot... +2025-04-05 07:39:29 | [maml_trainer] epoch #85 | Saved +2025-04-05 07:39:29 | [maml_trainer] epoch #85 | Time 140413.68 s +2025-04-05 07:39:29 | [maml_trainer] epoch #85 | EpochTime 1654.68 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.218 +Average/AverageReturn -61.2313 +Average/Iteration 85 +Average/MaxReturn -44.7326 +Average/MinReturn -175.881 +Average/NumEpisodes 120 +Average/StdReturn 19.1219 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96594 +GaussianMLPPolicy/KLAfter 0.00276423 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.10314e-05 +GaussianMLPPolicy/LossBefore -5.86112e-09 +GaussianMLPPolicy/dLoss 2.10256e-05 +Iteration 85 +MetaTest/Average/AverageDiscountedReturn -64.678 +MetaTest/Average/AverageReturn -64.678 +MetaTest/Average/Iteration 85 +MetaTest/Average/MaxReturn -45.6668 +MetaTest/Average/MinReturn -189.979 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 30.2242 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -64.678 +MetaTest/__unnamed_task__/AverageReturn -64.678 +MetaTest/__unnamed_task__/Iteration 85 +MetaTest/__unnamed_task__/MaxReturn -45.6668 +MetaTest/__unnamed_task__/MinReturn -189.979 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 30.2242 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.128e+06 +__unnamed_task__/AverageDiscountedReturn -31.218 +__unnamed_task__/AverageReturn -61.2313 +__unnamed_task__/Iteration 85 +__unnamed_task__/MaxReturn -44.7326 +__unnamed_task__/MinReturn -175.881 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 19.1219 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 08:02:44 | [maml_trainer] epoch #86 | Sampling for adapation and meta-testing... +2025-04-05 08:06:39 | [maml_trainer] epoch #86 | Finished meta-testing... +2025-04-05 08:06:39 | [maml_trainer] epoch #86 | Saving snapshot... +2025-04-05 08:07:00 | [maml_trainer] epoch #86 | Saved +2025-04-05 08:07:00 | [maml_trainer] epoch #86 | Time 142064.10 s +2025-04-05 08:07:00 | [maml_trainer] epoch #86 | EpochTime 1650.42 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.4549 +Average/AverageReturn -57.8577 +Average/Iteration 86 +Average/MaxReturn -43.7126 +Average/MinReturn -108.535 +Average/NumEpisodes 120 +Average/StdReturn 10.1488 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96649 +GaussianMLPPolicy/KLAfter 0.00285404 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.00010535 +GaussianMLPPolicy/LossBefore 1.56959e-08 +GaussianMLPPolicy/dLoss -0.000105334 +Iteration 86 +MetaTest/Average/AverageDiscountedReturn -60.9536 +MetaTest/Average/AverageReturn -60.9536 +MetaTest/Average/Iteration 86 +MetaTest/Average/MaxReturn -46.8809 +MetaTest/Average/MinReturn -111.45 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 15.0858 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.9536 +MetaTest/__unnamed_task__/AverageReturn -60.9536 +MetaTest/__unnamed_task__/Iteration 86 +MetaTest/__unnamed_task__/MaxReturn -46.8809 +MetaTest/__unnamed_task__/MinReturn -111.45 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 15.0858 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.176e+06 +__unnamed_task__/AverageDiscountedReturn -30.4549 +__unnamed_task__/AverageReturn -57.8577 +__unnamed_task__/Iteration 86 +__unnamed_task__/MaxReturn -43.7126 +__unnamed_task__/MinReturn -108.535 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.1488 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 08:30:26 | [maml_trainer] epoch #87 | Sampling for adapation and meta-testing... +2025-04-05 08:34:21 | [maml_trainer] epoch #87 | Finished meta-testing... +2025-04-05 08:34:21 | [maml_trainer] epoch #87 | Saving snapshot... +2025-04-05 08:34:41 | [maml_trainer] epoch #87 | Saved +2025-04-05 08:34:41 | [maml_trainer] epoch #87 | Time 143725.93 s +2025-04-05 08:34:41 | [maml_trainer] epoch #87 | EpochTime 1661.84 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.6752 +Average/AverageReturn -59.3497 +Average/Iteration 87 +Average/MaxReturn -42.4099 +Average/MinReturn -137.675 +Average/NumEpisodes 120 +Average/StdReturn 13.4154 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96587 +GaussianMLPPolicy/KLAfter 0.00259497 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.59603e-05 +GaussianMLPPolicy/LossBefore 7.70887e-09 +GaussianMLPPolicy/dLoss 5.5968e-05 +Iteration 87 +MetaTest/Average/AverageDiscountedReturn -57.1425 +MetaTest/Average/AverageReturn -57.1425 +MetaTest/Average/Iteration 87 +MetaTest/Average/MaxReturn -45.8172 +MetaTest/Average/MinReturn -86.2133 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.8958 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1425 +MetaTest/__unnamed_task__/AverageReturn -57.1425 +MetaTest/__unnamed_task__/Iteration 87 +MetaTest/__unnamed_task__/MaxReturn -45.8172 +MetaTest/__unnamed_task__/MinReturn -86.2133 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.8958 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.224e+06 +__unnamed_task__/AverageDiscountedReturn -30.6752 +__unnamed_task__/AverageReturn -59.3497 +__unnamed_task__/Iteration 87 +__unnamed_task__/MaxReturn -42.4099 +__unnamed_task__/MinReturn -137.675 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.4154 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 08:57:50 | [maml_trainer] epoch #88 | Sampling for adapation and meta-testing... +2025-04-05 09:01:40 | [maml_trainer] epoch #88 | Finished meta-testing... +2025-04-05 09:01:40 | [maml_trainer] epoch #88 | Saving snapshot... +2025-04-05 09:02:01 | [maml_trainer] epoch #88 | Saved +2025-04-05 09:02:01 | [maml_trainer] epoch #88 | Time 145365.33 s +2025-04-05 09:02:01 | [maml_trainer] epoch #88 | EpochTime 1639.39 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.0802 +Average/AverageReturn -63.3815 +Average/Iteration 88 +Average/MaxReturn -42.0779 +Average/MinReturn -193.346 +Average/NumEpisodes 120 +Average/StdReturn 26.5486 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96613 +GaussianMLPPolicy/KLAfter 0.00247862 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.37373e-05 +GaussianMLPPolicy/LossBefore -2.70208e-09 +GaussianMLPPolicy/dLoss 2.37346e-05 +Iteration 88 +MetaTest/Average/AverageDiscountedReturn -63.7654 +MetaTest/Average/AverageReturn -63.7654 +MetaTest/Average/Iteration 88 +MetaTest/Average/MaxReturn -47.0283 +MetaTest/Average/MinReturn -164.196 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 26.6234 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -63.7654 +MetaTest/__unnamed_task__/AverageReturn -63.7654 +MetaTest/__unnamed_task__/Iteration 88 +MetaTest/__unnamed_task__/MaxReturn -47.0283 +MetaTest/__unnamed_task__/MinReturn -164.196 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 26.6234 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.272e+06 +__unnamed_task__/AverageDiscountedReturn -31.0802 +__unnamed_task__/AverageReturn -63.3815 +__unnamed_task__/Iteration 88 +__unnamed_task__/MaxReturn -42.0779 +__unnamed_task__/MinReturn -193.346 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.5486 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 09:25:11 | [maml_trainer] epoch #89 | Sampling for adapation and meta-testing... +2025-04-05 09:29:03 | [maml_trainer] epoch #89 | Finished meta-testing... +2025-04-05 09:29:03 | [maml_trainer] epoch #89 | Saving snapshot... +2025-04-05 09:29:24 | [maml_trainer] epoch #89 | Saved +2025-04-05 09:29:24 | [maml_trainer] epoch #89 | Time 147008.24 s +2025-04-05 09:29:24 | [maml_trainer] epoch #89 | EpochTime 1642.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.6101 +Average/AverageReturn -58.3364 +Average/Iteration 89 +Average/MaxReturn -42.9804 +Average/MinReturn -190.57 +Average/NumEpisodes 120 +Average/StdReturn 24.5937 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96451 +GaussianMLPPolicy/KLAfter 0.00302948 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.7102e-05 +GaussianMLPPolicy/LossBefore -3.50674e-09 +GaussianMLPPolicy/dLoss 3.70985e-05 +Iteration 89 +MetaTest/Average/AverageDiscountedReturn -70.5178 +MetaTest/Average/AverageReturn -70.5178 +MetaTest/Average/Iteration 89 +MetaTest/Average/MaxReturn -46.3977 +MetaTest/Average/MinReturn -189.238 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 39.4415 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -70.5178 +MetaTest/__unnamed_task__/AverageReturn -70.5178 +MetaTest/__unnamed_task__/Iteration 89 +MetaTest/__unnamed_task__/MaxReturn -46.3977 +MetaTest/__unnamed_task__/MinReturn -189.238 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 39.4415 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.32e+06 +__unnamed_task__/AverageDiscountedReturn -29.6101 +__unnamed_task__/AverageReturn -58.3364 +__unnamed_task__/Iteration 89 +__unnamed_task__/MaxReturn -42.9804 +__unnamed_task__/MinReturn -190.57 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 24.5937 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 09:52:53 | [maml_trainer] epoch #90 | Sampling for adapation and meta-testing... +2025-04-05 09:56:49 | [maml_trainer] epoch #90 | Finished meta-testing... +2025-04-05 09:56:49 | [maml_trainer] epoch #90 | Saving snapshot... +2025-04-05 09:57:11 | [maml_trainer] epoch #90 | Saved +2025-04-05 09:57:11 | [maml_trainer] epoch #90 | Time 148675.20 s +2025-04-05 09:57:11 | [maml_trainer] epoch #90 | EpochTime 1666.95 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.8822 +Average/AverageReturn -59.5636 +Average/Iteration 90 +Average/MaxReturn -42.4041 +Average/MinReturn -180.245 +Average/NumEpisodes 120 +Average/StdReturn 23.6192 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96298 +GaussianMLPPolicy/KLAfter 0.00485447 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.81109e-05 +GaussianMLPPolicy/LossBefore 4.09285e-09 +GaussianMLPPolicy/dLoss 1.8115e-05 +Iteration 90 +MetaTest/Average/AverageDiscountedReturn -50.3863 +MetaTest/Average/AverageReturn -50.3863 +MetaTest/Average/Iteration 90 +MetaTest/Average/MaxReturn -40.4488 +MetaTest/Average/MinReturn -66.5881 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.8584 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3863 +MetaTest/__unnamed_task__/AverageReturn -50.3863 +MetaTest/__unnamed_task__/Iteration 90 +MetaTest/__unnamed_task__/MaxReturn -40.4488 +MetaTest/__unnamed_task__/MinReturn -66.5881 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.8584 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.368e+06 +__unnamed_task__/AverageDiscountedReturn -29.8822 +__unnamed_task__/AverageReturn -59.5636 +__unnamed_task__/Iteration 90 +__unnamed_task__/MaxReturn -42.4041 +__unnamed_task__/MinReturn -180.245 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 23.6192 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 10:21:11 | [maml_trainer] epoch #91 | Sampling for adapation and meta-testing... +2025-04-05 10:25:06 | [maml_trainer] epoch #91 | Finished meta-testing... +2025-04-05 10:25:06 | [maml_trainer] epoch #91 | Saving snapshot... +2025-04-05 10:25:27 | [maml_trainer] epoch #91 | Saved +2025-04-05 10:25:27 | [maml_trainer] epoch #91 | Time 150371.48 s +2025-04-05 10:25:27 | [maml_trainer] epoch #91 | EpochTime 1696.28 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.6358 +Average/AverageReturn -57.6889 +Average/Iteration 91 +Average/MaxReturn -41.064 +Average/MinReturn -171.374 +Average/NumEpisodes 120 +Average/StdReturn 20.5468 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96158 +GaussianMLPPolicy/KLAfter 0.00399884 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.80113e-05 +GaussianMLPPolicy/LossBefore -3.27826e-09 +GaussianMLPPolicy/dLoss 3.8008e-05 +Iteration 91 +MetaTest/Average/AverageDiscountedReturn -58.4129 +MetaTest/Average/AverageReturn -58.4129 +MetaTest/Average/Iteration 91 +MetaTest/Average/MaxReturn -42.5019 +MetaTest/Average/MinReturn -182.189 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 29.5125 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.4129 +MetaTest/__unnamed_task__/AverageReturn -58.4129 +MetaTest/__unnamed_task__/Iteration 91 +MetaTest/__unnamed_task__/MaxReturn -42.5019 +MetaTest/__unnamed_task__/MinReturn -182.189 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 29.5125 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.416e+06 +__unnamed_task__/AverageDiscountedReturn -29.6358 +__unnamed_task__/AverageReturn -57.6889 +__unnamed_task__/Iteration 91 +__unnamed_task__/MaxReturn -41.064 +__unnamed_task__/MinReturn -171.374 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.5468 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 10:48:56 | [maml_trainer] epoch #92 | Sampling for adapation and meta-testing... +2025-04-05 10:52:49 | [maml_trainer] epoch #92 | Finished meta-testing... +2025-04-05 10:52:49 | [maml_trainer] epoch #92 | Saving snapshot... +2025-04-05 10:53:10 | [maml_trainer] epoch #92 | Saved +2025-04-05 10:53:10 | [maml_trainer] epoch #92 | Time 152034.19 s +2025-04-05 10:53:10 | [maml_trainer] epoch #92 | EpochTime 1662.71 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.1623 +Average/AverageReturn -56.9068 +Average/Iteration 92 +Average/MaxReturn -41.7085 +Average/MinReturn -178.415 +Average/NumEpisodes 120 +Average/StdReturn 22.0849 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96133 +GaussianMLPPolicy/KLAfter 0.00440087 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.23922e-05 +GaussianMLPPolicy/LossBefore -3.27826e-09 +GaussianMLPPolicy/dLoss -1.23954e-05 +Iteration 92 +MetaTest/Average/AverageDiscountedReturn -55.6519 +MetaTest/Average/AverageReturn -55.6519 +MetaTest/Average/Iteration 92 +MetaTest/Average/MaxReturn -43.0697 +MetaTest/Average/MinReturn -88.4887 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.2443 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6519 +MetaTest/__unnamed_task__/AverageReturn -55.6519 +MetaTest/__unnamed_task__/Iteration 92 +MetaTest/__unnamed_task__/MaxReturn -43.0697 +MetaTest/__unnamed_task__/MinReturn -88.4887 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.2443 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.464e+06 +__unnamed_task__/AverageDiscountedReturn -29.1623 +__unnamed_task__/AverageReturn -56.9068 +__unnamed_task__/Iteration 92 +__unnamed_task__/MaxReturn -41.7085 +__unnamed_task__/MinReturn -178.415 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 22.0849 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 11:16:30 | [maml_trainer] epoch #93 | Sampling for adapation and meta-testing... +2025-04-05 11:20:26 | [maml_trainer] epoch #93 | Finished meta-testing... +2025-04-05 11:20:26 | [maml_trainer] epoch #93 | Saving snapshot... +2025-04-05 11:20:47 | [maml_trainer] epoch #93 | Saved +2025-04-05 11:20:47 | [maml_trainer] epoch #93 | Time 153691.55 s +2025-04-05 11:20:47 | [maml_trainer] epoch #93 | EpochTime 1657.36 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.4969 +Average/AverageReturn -53.2934 +Average/Iteration 93 +Average/MaxReturn -41.7825 +Average/MinReturn -94.8963 +Average/NumEpisodes 120 +Average/StdReturn 8.98511 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.96036 +GaussianMLPPolicy/KLAfter 0.00247976 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.21772e-05 +GaussianMLPPolicy/LossBefore 2.74181e-09 +GaussianMLPPolicy/dLoss -2.21744e-05 +Iteration 93 +MetaTest/Average/AverageDiscountedReturn -55.3694 +MetaTest/Average/AverageReturn -55.3694 +MetaTest/Average/Iteration 93 +MetaTest/Average/MaxReturn -46.6118 +MetaTest/Average/MinReturn -135.994 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 18.9397 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3694 +MetaTest/__unnamed_task__/AverageReturn -55.3694 +MetaTest/__unnamed_task__/Iteration 93 +MetaTest/__unnamed_task__/MaxReturn -46.6118 +MetaTest/__unnamed_task__/MinReturn -135.994 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 18.9397 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.512e+06 +__unnamed_task__/AverageDiscountedReturn -28.4969 +__unnamed_task__/AverageReturn -53.2934 +__unnamed_task__/Iteration 93 +__unnamed_task__/MaxReturn -41.7825 +__unnamed_task__/MinReturn -94.8963 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.98511 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 11:44:22 | [maml_trainer] epoch #94 | Sampling for adapation and meta-testing... +2025-04-05 11:48:17 | [maml_trainer] epoch #94 | Finished meta-testing... +2025-04-05 11:48:17 | [maml_trainer] epoch #94 | Saving snapshot... +2025-04-05 11:48:38 | [maml_trainer] epoch #94 | Saved +2025-04-05 11:48:38 | [maml_trainer] epoch #94 | Time 155362.62 s +2025-04-05 11:48:38 | [maml_trainer] epoch #94 | EpochTime 1671.06 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.8227 +Average/AverageReturn -54.5293 +Average/Iteration 94 +Average/MaxReturn -43.1441 +Average/MinReturn -144.361 +Average/NumEpisodes 120 +Average/StdReturn 12.5177 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95917 +GaussianMLPPolicy/KLAfter 0.00254408 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.97066e-05 +GaussianMLPPolicy/LossBefore 2.78155e-09 +GaussianMLPPolicy/dLoss 3.97094e-05 +Iteration 94 +MetaTest/Average/AverageDiscountedReturn -56.2704 +MetaTest/Average/AverageReturn -56.2704 +MetaTest/Average/Iteration 94 +MetaTest/Average/MaxReturn -47.3517 +MetaTest/Average/MinReturn -117.499 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.9112 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.2704 +MetaTest/__unnamed_task__/AverageReturn -56.2704 +MetaTest/__unnamed_task__/Iteration 94 +MetaTest/__unnamed_task__/MaxReturn -47.3517 +MetaTest/__unnamed_task__/MinReturn -117.499 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.9112 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.56e+06 +__unnamed_task__/AverageDiscountedReturn -28.8227 +__unnamed_task__/AverageReturn -54.5293 +__unnamed_task__/Iteration 94 +__unnamed_task__/MaxReturn -43.1441 +__unnamed_task__/MinReturn -144.361 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.5177 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 12:12:11 | [maml_trainer] epoch #95 | Sampling for adapation and meta-testing... +2025-04-05 12:16:12 | [maml_trainer] epoch #95 | Finished meta-testing... +2025-04-05 12:16:12 | [maml_trainer] epoch #95 | Saving snapshot... +2025-04-05 12:16:33 | [maml_trainer] epoch #95 | Saved +2025-04-05 12:16:33 | [maml_trainer] epoch #95 | Time 157037.41 s +2025-04-05 12:16:33 | [maml_trainer] epoch #95 | EpochTime 1674.79 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.6141 +Average/AverageReturn -53.5099 +Average/Iteration 95 +Average/MaxReturn -41.1638 +Average/MinReturn -125.74 +Average/NumEpisodes 120 +Average/StdReturn 10.6697 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95821 +GaussianMLPPolicy/KLAfter 0.00353217 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.54413e-05 +GaussianMLPPolicy/LossBefore 5.126e-09 +GaussianMLPPolicy/dLoss 4.54465e-05 +Iteration 95 +MetaTest/Average/AverageDiscountedReturn -50.2972 +MetaTest/Average/AverageReturn -50.2972 +MetaTest/Average/Iteration 95 +MetaTest/Average/MaxReturn -42.426 +MetaTest/Average/MinReturn -65.3995 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.22778 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2972 +MetaTest/__unnamed_task__/AverageReturn -50.2972 +MetaTest/__unnamed_task__/Iteration 95 +MetaTest/__unnamed_task__/MaxReturn -42.426 +MetaTest/__unnamed_task__/MinReturn -65.3995 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.22778 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.608e+06 +__unnamed_task__/AverageDiscountedReturn -28.6141 +__unnamed_task__/AverageReturn -53.5099 +__unnamed_task__/Iteration 95 +__unnamed_task__/MaxReturn -41.1638 +__unnamed_task__/MinReturn -125.74 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.6697 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 12:41:08 | [maml_trainer] epoch #96 | Sampling for adapation and meta-testing... +2025-04-05 12:45:19 | [maml_trainer] epoch #96 | Finished meta-testing... +2025-04-05 12:45:19 | [maml_trainer] epoch #96 | Saving snapshot... +2025-04-05 12:45:42 | [maml_trainer] epoch #96 | Saved +2025-04-05 12:45:42 | [maml_trainer] epoch #96 | Time 158786.44 s +2025-04-05 12:45:42 | [maml_trainer] epoch #96 | EpochTime 1749.03 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.1625 +Average/AverageReturn -53.4405 +Average/Iteration 96 +Average/MaxReturn -43.3048 +Average/MinReturn -157.223 +Average/NumEpisodes 120 +Average/StdReturn 14.5795 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95758 +GaussianMLPPolicy/KLAfter 0.00252138 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000104698 +GaussianMLPPolicy/LossBefore 7.2519e-09 +GaussianMLPPolicy/dLoss 0.000104706 +Iteration 96 +MetaTest/Average/AverageDiscountedReturn -57.0998 +MetaTest/Average/AverageReturn -57.0998 +MetaTest/Average/Iteration 96 +MetaTest/Average/MaxReturn -46.0531 +MetaTest/Average/MinReturn -118.561 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 15.276 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.0998 +MetaTest/__unnamed_task__/AverageReturn -57.0998 +MetaTest/__unnamed_task__/Iteration 96 +MetaTest/__unnamed_task__/MaxReturn -46.0531 +MetaTest/__unnamed_task__/MinReturn -118.561 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 15.276 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.656e+06 +__unnamed_task__/AverageDiscountedReturn -28.1625 +__unnamed_task__/AverageReturn -53.4405 +__unnamed_task__/Iteration 96 +__unnamed_task__/MaxReturn -43.3048 +__unnamed_task__/MinReturn -157.223 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.5795 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 13:09:46 | [maml_trainer] epoch #97 | Sampling for adapation and meta-testing... +2025-04-05 13:13:43 | [maml_trainer] epoch #97 | Finished meta-testing... +2025-04-05 13:13:43 | [maml_trainer] epoch #97 | Saving snapshot... +2025-04-05 13:14:04 | [maml_trainer] epoch #97 | Saved +2025-04-05 13:14:04 | [maml_trainer] epoch #97 | Time 160488.21 s +2025-04-05 13:14:04 | [maml_trainer] epoch #97 | EpochTime 1701.77 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4171 +Average/AverageReturn -52.0575 +Average/Iteration 97 +Average/MaxReturn -43.2805 +Average/MinReturn -70.0271 +Average/NumEpisodes 120 +Average/StdReturn 5.01085 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95779 +GaussianMLPPolicy/KLAfter 0.00252363 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.41512e-05 +GaussianMLPPolicy/LossBefore 1.02123e-08 +GaussianMLPPolicy/dLoss 2.41615e-05 +Iteration 97 +MetaTest/Average/AverageDiscountedReturn -52.619 +MetaTest/Average/AverageReturn -52.619 +MetaTest/Average/Iteration 97 +MetaTest/Average/MaxReturn -44.4421 +MetaTest/Average/MinReturn -65.8042 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.61183 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.619 +MetaTest/__unnamed_task__/AverageReturn -52.619 +MetaTest/__unnamed_task__/Iteration 97 +MetaTest/__unnamed_task__/MaxReturn -44.4421 +MetaTest/__unnamed_task__/MinReturn -65.8042 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.61183 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.704e+06 +__unnamed_task__/AverageDiscountedReturn -28.4171 +__unnamed_task__/AverageReturn -52.0575 +__unnamed_task__/Iteration 97 +__unnamed_task__/MaxReturn -43.2805 +__unnamed_task__/MinReturn -70.0271 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.01085 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 13:37:50 | [maml_trainer] epoch #98 | Sampling for adapation and meta-testing... +2025-04-05 13:41:43 | [maml_trainer] epoch #98 | Finished meta-testing... +2025-04-05 13:41:43 | [maml_trainer] epoch #98 | Saving snapshot... +2025-04-05 13:42:04 | [maml_trainer] epoch #98 | Saved +2025-04-05 13:42:04 | [maml_trainer] epoch #98 | Time 162168.70 s +2025-04-05 13:42:04 | [maml_trainer] epoch #98 | EpochTime 1680.49 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.194 +Average/AverageReturn -52.1139 +Average/Iteration 98 +Average/MaxReturn -42.1884 +Average/MinReturn -116.71 +Average/NumEpisodes 120 +Average/StdReturn 7.47425 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95696 +GaussianMLPPolicy/KLAfter 0.00261446 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.78363e-05 +GaussianMLPPolicy/LossBefore -1.15633e-08 +GaussianMLPPolicy/dLoss 1.78247e-05 +Iteration 98 +MetaTest/Average/AverageDiscountedReturn -55.3939 +MetaTest/Average/AverageReturn -55.3939 +MetaTest/Average/Iteration 98 +MetaTest/Average/MaxReturn -43.9058 +MetaTest/Average/MinReturn -130.889 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 18.0222 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3939 +MetaTest/__unnamed_task__/AverageReturn -55.3939 +MetaTest/__unnamed_task__/Iteration 98 +MetaTest/__unnamed_task__/MaxReturn -43.9058 +MetaTest/__unnamed_task__/MinReturn -130.889 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 18.0222 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.752e+06 +__unnamed_task__/AverageDiscountedReturn -28.194 +__unnamed_task__/AverageReturn -52.1139 +__unnamed_task__/Iteration 98 +__unnamed_task__/MaxReturn -42.1884 +__unnamed_task__/MinReturn -116.71 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.47425 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 14:05:21 | [maml_trainer] epoch #99 | Sampling for adapation and meta-testing... +2025-04-05 14:09:22 | [maml_trainer] epoch #99 | Finished meta-testing... +2025-04-05 14:09:22 | [maml_trainer] epoch #99 | Saving snapshot... +2025-04-05 14:09:43 | [maml_trainer] epoch #99 | Saved +2025-04-05 14:09:43 | [maml_trainer] epoch #99 | Time 163827.21 s +2025-04-05 14:09:43 | [maml_trainer] epoch #99 | EpochTime 1658.50 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0189 +Average/AverageReturn -51.6878 +Average/Iteration 99 +Average/MaxReturn -42.257 +Average/MinReturn -85.9253 +Average/NumEpisodes 120 +Average/StdReturn 6.03294 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95697 +GaussianMLPPolicy/KLAfter 0.0024304 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.85104e-06 +GaussianMLPPolicy/LossBefore -1.07288e-08 +GaussianMLPPolicy/dLoss 7.84032e-06 +Iteration 99 +MetaTest/Average/AverageDiscountedReturn -52.6126 +MetaTest/Average/AverageReturn -52.6126 +MetaTest/Average/Iteration 99 +MetaTest/Average/MaxReturn -44.7489 +MetaTest/Average/MinReturn -87.4205 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.79591 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6126 +MetaTest/__unnamed_task__/AverageReturn -52.6126 +MetaTest/__unnamed_task__/Iteration 99 +MetaTest/__unnamed_task__/MaxReturn -44.7489 +MetaTest/__unnamed_task__/MinReturn -87.4205 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.79591 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.8e+06 +__unnamed_task__/AverageDiscountedReturn -28.0189 +__unnamed_task__/AverageReturn -51.6878 +__unnamed_task__/Iteration 99 +__unnamed_task__/MaxReturn -42.257 +__unnamed_task__/MinReturn -85.9253 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.03294 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 14:33:06 | [maml_trainer] epoch #100 | Sampling for adapation and meta-testing... +2025-04-05 14:37:00 | [maml_trainer] epoch #100 | Finished meta-testing... +2025-04-05 14:37:00 | [maml_trainer] epoch #100 | Saving snapshot... +2025-04-05 14:37:21 | [maml_trainer] epoch #100 | Saved +2025-04-05 14:37:21 | [maml_trainer] epoch #100 | Time 165485.83 s +2025-04-05 14:37:21 | [maml_trainer] epoch #100 | EpochTime 1658.62 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.8419 +Average/AverageReturn -55.609 +Average/Iteration 100 +Average/MaxReturn -42.3302 +Average/MinReturn -179.318 +Average/NumEpisodes 120 +Average/StdReturn 21.1128 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.95596 +GaussianMLPPolicy/KLAfter 0.00154048 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.68168e-05 +GaussianMLPPolicy/LossBefore 6.41743e-09 +GaussianMLPPolicy/dLoss -2.68103e-05 +Iteration 100 +MetaTest/Average/AverageDiscountedReturn -53.6682 +MetaTest/Average/AverageReturn -53.6682 +MetaTest/Average/Iteration 100 +MetaTest/Average/MaxReturn -44.0246 +MetaTest/Average/MinReturn -77.3252 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.40881 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6682 +MetaTest/__unnamed_task__/AverageReturn -53.6682 +MetaTest/__unnamed_task__/Iteration 100 +MetaTest/__unnamed_task__/MaxReturn -44.0246 +MetaTest/__unnamed_task__/MinReturn -77.3252 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.40881 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.848e+06 +__unnamed_task__/AverageDiscountedReturn -28.8419 +__unnamed_task__/AverageReturn -55.609 +__unnamed_task__/Iteration 100 +__unnamed_task__/MaxReturn -42.3302 +__unnamed_task__/MinReturn -179.318 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 21.1128 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 15:00:59 | [maml_trainer] epoch #101 | Sampling for adapation and meta-testing... +2025-04-05 15:04:54 | [maml_trainer] epoch #101 | Finished meta-testing... +2025-04-05 15:04:54 | [maml_trainer] epoch #101 | Saving snapshot... +2025-04-05 15:05:15 | [maml_trainer] epoch #101 | Saved +2025-04-05 15:05:15 | [maml_trainer] epoch #101 | Time 167159.51 s +2025-04-05 15:05:15 | [maml_trainer] epoch #101 | EpochTime 1673.68 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.1193 +Average/AverageReturn -52.7379 +Average/Iteration 101 +Average/MaxReturn 261.574 +Average/MinReturn -177.699 +Average/NumEpisodes 120 +Average/StdReturn 34.7779 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9526 +GaussianMLPPolicy/KLAfter 0.00266528 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.1448e-06 +GaussianMLPPolicy/LossBefore 9.93411e-10 +GaussianMLPPolicy/dLoss 1.1458e-06 +Iteration 101 +MetaTest/Average/AverageDiscountedReturn -50.6922 +MetaTest/Average/AverageReturn -50.6922 +MetaTest/Average/Iteration 101 +MetaTest/Average/MaxReturn -39.3108 +MetaTest/Average/MinReturn -72.2192 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.81403 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6922 +MetaTest/__unnamed_task__/AverageReturn -50.6922 +MetaTest/__unnamed_task__/Iteration 101 +MetaTest/__unnamed_task__/MaxReturn -39.3108 +MetaTest/__unnamed_task__/MinReturn -72.2192 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.81403 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.896e+06 +__unnamed_task__/AverageDiscountedReturn -28.1193 +__unnamed_task__/AverageReturn -52.7379 +__unnamed_task__/Iteration 101 +__unnamed_task__/MaxReturn 261.574 +__unnamed_task__/MinReturn -177.699 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 34.7779 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 15:28:47 | [maml_trainer] epoch #102 | Sampling for adapation and meta-testing... +2025-04-05 15:32:41 | [maml_trainer] epoch #102 | Finished meta-testing... +2025-04-05 15:32:41 | [maml_trainer] epoch #102 | Saving snapshot... +2025-04-05 15:33:02 | [maml_trainer] epoch #102 | Saved +2025-04-05 15:33:02 | [maml_trainer] epoch #102 | Time 168826.56 s +2025-04-05 15:33:02 | [maml_trainer] epoch #102 | EpochTime 1667.05 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9285 +Average/AverageReturn -55.2858 +Average/Iteration 102 +Average/MaxReturn -42.3545 +Average/MinReturn -164.804 +Average/NumEpisodes 120 +Average/StdReturn 19.6098 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94872 +GaussianMLPPolicy/KLAfter 0.00289561 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.64122e-05 +GaussianMLPPolicy/LossBefore 8.42412e-09 +GaussianMLPPolicy/dLoss 2.64206e-05 +Iteration 102 +MetaTest/Average/AverageDiscountedReturn -53.0887 +MetaTest/Average/AverageReturn -53.0887 +MetaTest/Average/Iteration 102 +MetaTest/Average/MaxReturn -43.3693 +MetaTest/Average/MinReturn -102.614 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.3653 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0887 +MetaTest/__unnamed_task__/AverageReturn -53.0887 +MetaTest/__unnamed_task__/Iteration 102 +MetaTest/__unnamed_task__/MaxReturn -43.3693 +MetaTest/__unnamed_task__/MinReturn -102.614 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.3653 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.944e+06 +__unnamed_task__/AverageDiscountedReturn -28.9285 +__unnamed_task__/AverageReturn -55.2858 +__unnamed_task__/Iteration 102 +__unnamed_task__/MaxReturn -42.3545 +__unnamed_task__/MinReturn -164.804 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 19.6098 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 15:56:42 | [maml_trainer] epoch #103 | Sampling for adapation and meta-testing... +2025-04-05 16:00:43 | [maml_trainer] epoch #103 | Finished meta-testing... +2025-04-05 16:00:43 | [maml_trainer] epoch #103 | Saving snapshot... +2025-04-05 16:01:05 | [maml_trainer] epoch #103 | Saved +2025-04-05 16:01:05 | [maml_trainer] epoch #103 | Time 170509.65 s +2025-04-05 16:01:05 | [maml_trainer] epoch #103 | EpochTime 1683.09 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.2038 +Average/AverageReturn -51.9189 +Average/Iteration 103 +Average/MaxReturn -39.4598 +Average/MinReturn -108.832 +Average/NumEpisodes 120 +Average/StdReturn 7.40233 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.946 +GaussianMLPPolicy/KLAfter 0.00264905 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.79491e-05 +GaussianMLPPolicy/LossBefore -7.82808e-09 +GaussianMLPPolicy/dLoss -3.7957e-05 +Iteration 103 +MetaTest/Average/AverageDiscountedReturn -53.3658 +MetaTest/Average/AverageReturn -53.3658 +MetaTest/Average/Iteration 103 +MetaTest/Average/MaxReturn -44.849 +MetaTest/Average/MinReturn -63.2012 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.67582 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3658 +MetaTest/__unnamed_task__/AverageReturn -53.3658 +MetaTest/__unnamed_task__/Iteration 103 +MetaTest/__unnamed_task__/MaxReturn -44.849 +MetaTest/__unnamed_task__/MinReturn -63.2012 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.67582 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 4.992e+06 +__unnamed_task__/AverageDiscountedReturn -28.2038 +__unnamed_task__/AverageReturn -51.9189 +__unnamed_task__/Iteration 103 +__unnamed_task__/MaxReturn -39.4598 +__unnamed_task__/MinReturn -108.832 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.40233 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 16:26:05 | [maml_trainer] epoch #104 | Sampling for adapation and meta-testing... +2025-04-05 16:30:11 | [maml_trainer] epoch #104 | Finished meta-testing... +2025-04-05 16:30:11 | [maml_trainer] epoch #104 | Saving snapshot... +2025-04-05 16:30:34 | [maml_trainer] epoch #104 | Saved +2025-04-05 16:30:34 | [maml_trainer] epoch #104 | Time 172278.06 s +2025-04-05 16:30:34 | [maml_trainer] epoch #104 | EpochTime 1768.41 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5822 +Average/AverageReturn -52.5687 +Average/Iteration 104 +Average/MaxReturn -42.4986 +Average/MinReturn -74.8981 +Average/NumEpisodes 120 +Average/StdReturn 5.50724 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9436 +GaussianMLPPolicy/KLAfter 0.00194529 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.58121e-05 +GaussianMLPPolicy/LossBefore 1.48614e-08 +GaussianMLPPolicy/dLoss -7.57972e-05 +Iteration 104 +MetaTest/Average/AverageDiscountedReturn -51.1678 +MetaTest/Average/AverageReturn -51.1678 +MetaTest/Average/Iteration 104 +MetaTest/Average/MaxReturn -45.126 +MetaTest/Average/MinReturn -61.7353 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.19287 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1678 +MetaTest/__unnamed_task__/AverageReturn -51.1678 +MetaTest/__unnamed_task__/Iteration 104 +MetaTest/__unnamed_task__/MaxReturn -45.126 +MetaTest/__unnamed_task__/MinReturn -61.7353 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.19287 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.04e+06 +__unnamed_task__/AverageDiscountedReturn -28.5822 +__unnamed_task__/AverageReturn -52.5687 +__unnamed_task__/Iteration 104 +__unnamed_task__/MaxReturn -42.4986 +__unnamed_task__/MinReturn -74.8981 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.50724 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 16:55:20 | [maml_trainer] epoch #105 | Sampling for adapation and meta-testing... +2025-04-05 16:59:29 | [maml_trainer] epoch #105 | Finished meta-testing... +2025-04-05 16:59:29 | [maml_trainer] epoch #105 | Saving snapshot... +2025-04-05 16:59:52 | [maml_trainer] epoch #105 | Saved +2025-04-05 16:59:52 | [maml_trainer] epoch #105 | Time 174036.52 s +2025-04-05 16:59:52 | [maml_trainer] epoch #105 | EpochTime 1758.45 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.7281 +Average/AverageReturn -53.7593 +Average/Iteration 105 +Average/MaxReturn -42.3685 +Average/MinReturn -166.709 +Average/NumEpisodes 120 +Average/StdReturn 12.2198 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.94061 +GaussianMLPPolicy/KLAfter 0.00114982 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.98474e-05 +GaussianMLPPolicy/LossBefore -1.49409e-08 +GaussianMLPPolicy/dLoss 2.98325e-05 +Iteration 105 +MetaTest/Average/AverageDiscountedReturn -51.5374 +MetaTest/Average/AverageReturn -51.5374 +MetaTest/Average/Iteration 105 +MetaTest/Average/MaxReturn -44.8026 +MetaTest/Average/MinReturn -60.1001 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.48314 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5374 +MetaTest/__unnamed_task__/AverageReturn -51.5374 +MetaTest/__unnamed_task__/Iteration 105 +MetaTest/__unnamed_task__/MaxReturn -44.8026 +MetaTest/__unnamed_task__/MinReturn -60.1001 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.48314 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.088e+06 +__unnamed_task__/AverageDiscountedReturn -28.7281 +__unnamed_task__/AverageReturn -53.7593 +__unnamed_task__/Iteration 105 +__unnamed_task__/MaxReturn -42.3685 +__unnamed_task__/MinReturn -166.709 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.2198 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 17:24:42 | [maml_trainer] epoch #106 | Sampling for adapation and meta-testing... +2025-04-05 17:28:54 | [maml_trainer] epoch #106 | Finished meta-testing... +2025-04-05 17:28:54 | [maml_trainer] epoch #106 | Saving snapshot... +2025-04-05 17:29:16 | [maml_trainer] epoch #106 | Saved +2025-04-05 17:29:16 | [maml_trainer] epoch #106 | Time 175800.91 s +2025-04-05 17:29:16 | [maml_trainer] epoch #106 | EpochTime 1764.39 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.7742 +Average/AverageReturn -53.5435 +Average/Iteration 106 +Average/MaxReturn -41.8378 +Average/MinReturn -141.789 +Average/NumEpisodes 120 +Average/StdReturn 10.0697 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93676 +GaussianMLPPolicy/KLAfter 0.00274419 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000101878 +GaussianMLPPolicy/LossBefore -4.33127e-09 +GaussianMLPPolicy/dLoss 0.000101874 +Iteration 106 +MetaTest/Average/AverageDiscountedReturn -52.8986 +MetaTest/Average/AverageReturn -52.8986 +MetaTest/Average/Iteration 106 +MetaTest/Average/MaxReturn -46.1241 +MetaTest/Average/MinReturn -69.6802 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.07702 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8986 +MetaTest/__unnamed_task__/AverageReturn -52.8986 +MetaTest/__unnamed_task__/Iteration 106 +MetaTest/__unnamed_task__/MaxReturn -46.1241 +MetaTest/__unnamed_task__/MinReturn -69.6802 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.07702 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.136e+06 +__unnamed_task__/AverageDiscountedReturn -28.7742 +__unnamed_task__/AverageReturn -53.5435 +__unnamed_task__/Iteration 106 +__unnamed_task__/MaxReturn -41.8378 +__unnamed_task__/MinReturn -141.789 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.0697 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-05 17:54:04 | [maml_trainer] epoch #107 | Sampling for adapation and meta-testing... +2025-04-05 17:58:11 | [maml_trainer] epoch #107 | Finished meta-testing... +2025-04-05 17:58:11 | [maml_trainer] epoch #107 | Saving snapshot... +2025-04-05 17:58:34 | [maml_trainer] epoch #107 | Saved +2025-04-05 17:58:34 | [maml_trainer] epoch #107 | Time 177558.42 s +2025-04-05 17:58:34 | [maml_trainer] epoch #107 | EpochTime 1757.51 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6588 +Average/AverageReturn -52.6623 +Average/Iteration 107 +Average/MaxReturn -41.6545 +Average/MinReturn -70.4714 +Average/NumEpisodes 120 +Average/StdReturn 5.4978 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93503 +GaussianMLPPolicy/KLAfter 0.00175562 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.06459e-06 +GaussianMLPPolicy/LossBefore -1.41064e-08 +GaussianMLPPolicy/dLoss -8.07869e-06 +Iteration 107 +MetaTest/Average/AverageDiscountedReturn -52.2063 +MetaTest/Average/AverageReturn -52.2063 +MetaTest/Average/Iteration 107 +MetaTest/Average/MaxReturn -44.5888 +MetaTest/Average/MinReturn -65.5914 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.23935 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2063 +MetaTest/__unnamed_task__/AverageReturn -52.2063 +MetaTest/__unnamed_task__/Iteration 107 +MetaTest/__unnamed_task__/MaxReturn -44.5888 +MetaTest/__unnamed_task__/MinReturn -65.5914 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.23935 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.184e+06 +__unnamed_task__/AverageDiscountedReturn -28.6588 +__unnamed_task__/AverageReturn -52.6623 +__unnamed_task__/Iteration 107 +__unnamed_task__/MaxReturn -41.6545 +__unnamed_task__/MinReturn -70.4714 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.4978 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 18:23:21 | [maml_trainer] epoch #108 | Sampling for adapation and meta-testing... +2025-04-05 18:27:32 | [maml_trainer] epoch #108 | Finished meta-testing... +2025-04-05 18:27:32 | [maml_trainer] epoch #108 | Saving snapshot... +2025-04-05 18:27:55 | [maml_trainer] epoch #108 | Saved +2025-04-05 18:27:55 | [maml_trainer] epoch #108 | Time 179319.37 s +2025-04-05 18:27:55 | [maml_trainer] epoch #108 | EpochTime 1760.95 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3556 +Average/AverageReturn -51.8739 +Average/Iteration 108 +Average/MaxReturn -43.1072 +Average/MinReturn -73.4435 +Average/NumEpisodes 120 +Average/StdReturn 5.15773 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.93403 +GaussianMLPPolicy/KLAfter 0.00222565 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.92374e-05 +GaussianMLPPolicy/LossBefore -5.5631e-10 +GaussianMLPPolicy/dLoss 1.92368e-05 +Iteration 108 +MetaTest/Average/AverageDiscountedReturn -53.5447 +MetaTest/Average/AverageReturn -53.5447 +MetaTest/Average/Iteration 108 +MetaTest/Average/MaxReturn -48.3854 +MetaTest/Average/MinReturn -66.3425 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.31139 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5447 +MetaTest/__unnamed_task__/AverageReturn -53.5447 +MetaTest/__unnamed_task__/Iteration 108 +MetaTest/__unnamed_task__/MaxReturn -48.3854 +MetaTest/__unnamed_task__/MinReturn -66.3425 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.31139 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.232e+06 +__unnamed_task__/AverageDiscountedReturn -28.3556 +__unnamed_task__/AverageReturn -51.8739 +__unnamed_task__/Iteration 108 +__unnamed_task__/MaxReturn -43.1072 +__unnamed_task__/MinReturn -73.4435 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.15773 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 18:52:38 | [maml_trainer] epoch #109 | Sampling for adapation and meta-testing... +2025-04-05 18:56:45 | [maml_trainer] epoch #109 | Finished meta-testing... +2025-04-05 18:56:45 | [maml_trainer] epoch #109 | Saving snapshot... +2025-04-05 18:57:08 | [maml_trainer] epoch #109 | Saved +2025-04-05 18:57:08 | [maml_trainer] epoch #109 | Time 181072.27 s +2025-04-05 18:57:08 | [maml_trainer] epoch #109 | EpochTime 1752.89 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8856 +Average/AverageReturn -53.2025 +Average/Iteration 109 +Average/MaxReturn -43.3215 +Average/MinReturn -70.5487 +Average/NumEpisodes 120 +Average/StdReturn 5.39865 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9325 +GaussianMLPPolicy/KLAfter 0.00421949 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.84231e-06 +GaussianMLPPolicy/LossBefore 2.02656e-09 +GaussianMLPPolicy/dLoss 3.84434e-06 +Iteration 109 +MetaTest/Average/AverageDiscountedReturn -51.9575 +MetaTest/Average/AverageReturn -51.9575 +MetaTest/Average/Iteration 109 +MetaTest/Average/MaxReturn -43.9584 +MetaTest/Average/MinReturn -65.8749 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.60646 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9575 +MetaTest/__unnamed_task__/AverageReturn -51.9575 +MetaTest/__unnamed_task__/Iteration 109 +MetaTest/__unnamed_task__/MaxReturn -43.9584 +MetaTest/__unnamed_task__/MinReturn -65.8749 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.60646 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.28e+06 +__unnamed_task__/AverageDiscountedReturn -28.8856 +__unnamed_task__/AverageReturn -53.2025 +__unnamed_task__/Iteration 109 +__unnamed_task__/MaxReturn -43.3215 +__unnamed_task__/MinReturn -70.5487 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.39865 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 19:21:59 | [maml_trainer] epoch #110 | Sampling for adapation and meta-testing... +2025-04-05 19:26:12 | [maml_trainer] epoch #110 | Finished meta-testing... +2025-04-05 19:26:12 | [maml_trainer] epoch #110 | Saving snapshot... +2025-04-05 19:26:35 | [maml_trainer] epoch #110 | Saved +2025-04-05 19:26:35 | [maml_trainer] epoch #110 | Time 182839.42 s +2025-04-05 19:26:35 | [maml_trainer] epoch #110 | EpochTime 1767.15 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6536 +Average/AverageReturn -52.5786 +Average/Iteration 110 +Average/MaxReturn -41.9928 +Average/MinReturn -65.0309 +Average/NumEpisodes 120 +Average/StdReturn 4.21114 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9317 +GaussianMLPPolicy/KLAfter 0.00342693 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.49458e-05 +GaussianMLPPolicy/LossBefore -1.58151e-08 +GaussianMLPPolicy/dLoss -3.49617e-05 +Iteration 110 +MetaTest/Average/AverageDiscountedReturn -53.169 +MetaTest/Average/AverageReturn -53.169 +MetaTest/Average/Iteration 110 +MetaTest/Average/MaxReturn -44.7929 +MetaTest/Average/MinReturn -65.4943 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.56463 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.169 +MetaTest/__unnamed_task__/AverageReturn -53.169 +MetaTest/__unnamed_task__/Iteration 110 +MetaTest/__unnamed_task__/MaxReturn -44.7929 +MetaTest/__unnamed_task__/MinReturn -65.4943 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.56463 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.328e+06 +__unnamed_task__/AverageDiscountedReturn -28.6536 +__unnamed_task__/AverageReturn -52.5786 +__unnamed_task__/Iteration 110 +__unnamed_task__/MaxReturn -41.9928 +__unnamed_task__/MinReturn -65.0309 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.21114 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 19:51:35 | [maml_trainer] epoch #111 | Sampling for adapation and meta-testing... +2025-04-05 19:55:48 | [maml_trainer] epoch #111 | Finished meta-testing... +2025-04-05 19:55:48 | [maml_trainer] epoch #111 | Saving snapshot... +2025-04-05 19:56:11 | [maml_trainer] epoch #111 | Saved +2025-04-05 19:56:11 | [maml_trainer] epoch #111 | Time 184615.40 s +2025-04-05 19:56:11 | [maml_trainer] epoch #111 | EpochTime 1775.97 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.7541 +Average/AverageReturn -52.8121 +Average/Iteration 111 +Average/MaxReturn -42.9781 +Average/MinReturn -66.7746 +Average/NumEpisodes 120 +Average/StdReturn 4.7869 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92895 +GaussianMLPPolicy/KLAfter 0.00245505 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.11819e-05 +GaussianMLPPolicy/LossBefore 1.5378e-08 +GaussianMLPPolicy/dLoss -7.11666e-05 +Iteration 111 +MetaTest/Average/AverageDiscountedReturn -52.5374 +MetaTest/Average/AverageReturn -52.5374 +MetaTest/Average/Iteration 111 +MetaTest/Average/MaxReturn -45.8182 +MetaTest/Average/MinReturn -66.2827 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.41541 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5374 +MetaTest/__unnamed_task__/AverageReturn -52.5374 +MetaTest/__unnamed_task__/Iteration 111 +MetaTest/__unnamed_task__/MaxReturn -45.8182 +MetaTest/__unnamed_task__/MinReturn -66.2827 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.41541 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.376e+06 +__unnamed_task__/AverageDiscountedReturn -28.7541 +__unnamed_task__/AverageReturn -52.8121 +__unnamed_task__/Iteration 111 +__unnamed_task__/MaxReturn -42.9781 +__unnamed_task__/MinReturn -66.7746 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.7869 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 20:21:02 | [maml_trainer] epoch #112 | Sampling for adapation and meta-testing... +2025-04-05 20:25:09 | [maml_trainer] epoch #112 | Finished meta-testing... +2025-04-05 20:25:09 | [maml_trainer] epoch #112 | Saving snapshot... +2025-04-05 20:25:31 | [maml_trainer] epoch #112 | Saved +2025-04-05 20:25:31 | [maml_trainer] epoch #112 | Time 186375.85 s +2025-04-05 20:25:31 | [maml_trainer] epoch #112 | EpochTime 1760.44 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.0605 +Average/AverageReturn -53.8654 +Average/Iteration 112 +Average/MaxReturn -44.8967 +Average/MinReturn -75.1636 +Average/NumEpisodes 120 +Average/StdReturn 5.50645 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92621 +GaussianMLPPolicy/KLAfter 0.0021751 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.23495e-05 +GaussianMLPPolicy/LossBefore 1.44641e-08 +GaussianMLPPolicy/dLoss 2.2364e-05 +Iteration 112 +MetaTest/Average/AverageDiscountedReturn -54.2765 +MetaTest/Average/AverageReturn -54.2765 +MetaTest/Average/Iteration 112 +MetaTest/Average/MaxReturn -45.6425 +MetaTest/Average/MinReturn -64.2643 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.93218 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2765 +MetaTest/__unnamed_task__/AverageReturn -54.2765 +MetaTest/__unnamed_task__/Iteration 112 +MetaTest/__unnamed_task__/MaxReturn -45.6425 +MetaTest/__unnamed_task__/MinReturn -64.2643 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.93218 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.424e+06 +__unnamed_task__/AverageDiscountedReturn -29.0605 +__unnamed_task__/AverageReturn -53.8654 +__unnamed_task__/Iteration 112 +__unnamed_task__/MaxReturn -44.8967 +__unnamed_task__/MinReturn -75.1636 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.50645 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 20:50:29 | [maml_trainer] epoch #113 | Sampling for adapation and meta-testing... +2025-04-05 20:54:34 | [maml_trainer] epoch #113 | Finished meta-testing... +2025-04-05 20:54:34 | [maml_trainer] epoch #113 | Saving snapshot... +2025-04-05 20:54:57 | [maml_trainer] epoch #113 | Saved +2025-04-05 20:54:57 | [maml_trainer] epoch #113 | Time 188141.25 s +2025-04-05 20:54:57 | [maml_trainer] epoch #113 | EpochTime 1765.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.898 +Average/AverageReturn -53.4271 +Average/Iteration 113 +Average/MaxReturn -43.4533 +Average/MinReturn -70.7429 +Average/NumEpisodes 120 +Average/StdReturn 5.15235 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92437 +GaussianMLPPolicy/KLAfter 0.00299913 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.40273e-05 +GaussianMLPPolicy/LossBefore -1.98682e-08 +GaussianMLPPolicy/dLoss -2.40472e-05 +Iteration 113 +MetaTest/Average/AverageDiscountedReturn -51.7198 +MetaTest/Average/AverageReturn -51.7198 +MetaTest/Average/Iteration 113 +MetaTest/Average/MaxReturn -44.9282 +MetaTest/Average/MinReturn -62.358 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.44341 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7198 +MetaTest/__unnamed_task__/AverageReturn -51.7198 +MetaTest/__unnamed_task__/Iteration 113 +MetaTest/__unnamed_task__/MaxReturn -44.9282 +MetaTest/__unnamed_task__/MinReturn -62.358 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.44341 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.472e+06 +__unnamed_task__/AverageDiscountedReturn -28.898 +__unnamed_task__/AverageReturn -53.4271 +__unnamed_task__/Iteration 113 +__unnamed_task__/MaxReturn -43.4533 +__unnamed_task__/MinReturn -70.7429 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.15235 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 21:19:56 | [maml_trainer] epoch #114 | Sampling for adapation and meta-testing... +2025-04-05 21:24:10 | [maml_trainer] epoch #114 | Finished meta-testing... +2025-04-05 21:24:10 | [maml_trainer] epoch #114 | Saving snapshot... +2025-04-05 21:24:33 | [maml_trainer] epoch #114 | Saved +2025-04-05 21:24:33 | [maml_trainer] epoch #114 | Time 189917.52 s +2025-04-05 21:24:33 | [maml_trainer] epoch #114 | EpochTime 1776.26 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.7785 +Average/AverageReturn -53.0215 +Average/Iteration 114 +Average/MaxReturn -43.3184 +Average/MinReturn -79.4892 +Average/NumEpisodes 120 +Average/StdReturn 5.98586 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92258 +GaussianMLPPolicy/KLAfter 0.00310095 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.57114e-05 +GaussianMLPPolicy/LossBefore 2.6226e-08 +GaussianMLPPolicy/dLoss -5.56852e-05 +Iteration 114 +MetaTest/Average/AverageDiscountedReturn -53.3862 +MetaTest/Average/AverageReturn -53.3862 +MetaTest/Average/Iteration 114 +MetaTest/Average/MaxReturn -46.3585 +MetaTest/Average/MinReturn -64.6373 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.45998 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3862 +MetaTest/__unnamed_task__/AverageReturn -53.3862 +MetaTest/__unnamed_task__/Iteration 114 +MetaTest/__unnamed_task__/MaxReturn -46.3585 +MetaTest/__unnamed_task__/MinReturn -64.6373 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.45998 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.52e+06 +__unnamed_task__/AverageDiscountedReturn -28.7785 +__unnamed_task__/AverageReturn -53.0215 +__unnamed_task__/Iteration 114 +__unnamed_task__/MaxReturn -43.3184 +__unnamed_task__/MinReturn -79.4892 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.98586 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 21:49:53 | [maml_trainer] epoch #115 | Sampling for adapation and meta-testing... +2025-04-05 21:54:01 | [maml_trainer] epoch #115 | Finished meta-testing... +2025-04-05 21:54:01 | [maml_trainer] epoch #115 | Saving snapshot... +2025-04-05 21:54:24 | [maml_trainer] epoch #115 | Saved +2025-04-05 21:54:24 | [maml_trainer] epoch #115 | Time 191708.81 s +2025-04-05 21:54:24 | [maml_trainer] epoch #115 | EpochTime 1791.30 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.3548 +Average/AverageReturn -54.002 +Average/Iteration 115 +Average/MaxReturn -43.507 +Average/MinReturn -77.016 +Average/NumEpisodes 120 +Average/StdReturn 5.78658 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92168 +GaussianMLPPolicy/KLAfter 0.00492031 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000151641 +GaussianMLPPolicy/LossBefore -1.71264e-08 +GaussianMLPPolicy/dLoss -0.000151658 +Iteration 115 +MetaTest/Average/AverageDiscountedReturn -53.3711 +MetaTest/Average/AverageReturn -53.3711 +MetaTest/Average/Iteration 115 +MetaTest/Average/MaxReturn -43.7762 +MetaTest/Average/MinReturn -63.603 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.32031 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.3711 +MetaTest/__unnamed_task__/AverageReturn -53.3711 +MetaTest/__unnamed_task__/Iteration 115 +MetaTest/__unnamed_task__/MaxReturn -43.7762 +MetaTest/__unnamed_task__/MinReturn -63.603 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.32031 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.568e+06 +__unnamed_task__/AverageDiscountedReturn -29.3548 +__unnamed_task__/AverageReturn -54.002 +__unnamed_task__/Iteration 115 +__unnamed_task__/MaxReturn -43.507 +__unnamed_task__/MinReturn -77.016 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.78658 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 22:19:18 | [maml_trainer] epoch #116 | Sampling for adapation and meta-testing... +2025-04-05 22:23:27 | [maml_trainer] epoch #116 | Finished meta-testing... +2025-04-05 22:23:27 | [maml_trainer] epoch #116 | Saving snapshot... +2025-04-05 22:23:49 | [maml_trainer] epoch #116 | Saved +2025-04-05 22:23:49 | [maml_trainer] epoch #116 | Time 193473.88 s +2025-04-05 22:23:49 | [maml_trainer] epoch #116 | EpochTime 1765.07 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6798 +Average/AverageReturn -52.651 +Average/Iteration 116 +Average/MaxReturn -44.4265 +Average/MinReturn -68.5021 +Average/NumEpisodes 120 +Average/StdReturn 5.03753 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.92011 +GaussianMLPPolicy/KLAfter 0.00579713 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000203099 +GaussianMLPPolicy/LossBefore 5.126e-09 +GaussianMLPPolicy/dLoss 0.000203104 +Iteration 116 +MetaTest/Average/AverageDiscountedReturn -52.8902 +MetaTest/Average/AverageReturn -52.8902 +MetaTest/Average/Iteration 116 +MetaTest/Average/MaxReturn -47.3906 +MetaTest/Average/MinReturn -61.4671 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.60679 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8902 +MetaTest/__unnamed_task__/AverageReturn -52.8902 +MetaTest/__unnamed_task__/Iteration 116 +MetaTest/__unnamed_task__/MaxReturn -47.3906 +MetaTest/__unnamed_task__/MinReturn -61.4671 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.60679 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.616e+06 +__unnamed_task__/AverageDiscountedReturn -28.6798 +__unnamed_task__/AverageReturn -52.651 +__unnamed_task__/Iteration 116 +__unnamed_task__/MaxReturn -44.4265 +__unnamed_task__/MinReturn -68.5021 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.03753 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 22:48:54 | [maml_trainer] epoch #117 | Sampling for adapation and meta-testing... +2025-04-05 22:53:09 | [maml_trainer] epoch #117 | Finished meta-testing... +2025-04-05 22:53:09 | [maml_trainer] epoch #117 | Saving snapshot... +2025-04-05 22:53:32 | [maml_trainer] epoch #117 | Saved +2025-04-05 22:53:32 | [maml_trainer] epoch #117 | Time 195256.09 s +2025-04-05 22:53:32 | [maml_trainer] epoch #117 | EpochTime 1782.20 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.0705 +Average/AverageReturn -53.0793 +Average/Iteration 117 +Average/MaxReturn -44.2464 +Average/MinReturn -71.2705 +Average/NumEpisodes 120 +Average/StdReturn 4.52633 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.91953 +GaussianMLPPolicy/KLAfter 0.00552407 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000162094 +GaussianMLPPolicy/LossBefore 3.21865e-09 +GaussianMLPPolicy/dLoss 0.000162097 +Iteration 117 +MetaTest/Average/AverageDiscountedReturn -53.2476 +MetaTest/Average/AverageReturn -53.2476 +MetaTest/Average/Iteration 117 +MetaTest/Average/MaxReturn -47.1193 +MetaTest/Average/MinReturn -83.801 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.72557 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.2476 +MetaTest/__unnamed_task__/AverageReturn -53.2476 +MetaTest/__unnamed_task__/Iteration 117 +MetaTest/__unnamed_task__/MaxReturn -47.1193 +MetaTest/__unnamed_task__/MinReturn -83.801 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.72557 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.664e+06 +__unnamed_task__/AverageDiscountedReturn -29.0705 +__unnamed_task__/AverageReturn -53.0793 +__unnamed_task__/Iteration 117 +__unnamed_task__/MaxReturn -44.2464 +__unnamed_task__/MinReturn -71.2705 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.52633 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 23:19:01 | [maml_trainer] epoch #118 | Sampling for adapation and meta-testing... +2025-04-05 23:23:17 | [maml_trainer] epoch #118 | Finished meta-testing... +2025-04-05 23:23:17 | [maml_trainer] epoch #118 | Saving snapshot... +2025-04-05 23:23:40 | [maml_trainer] epoch #118 | Saved +2025-04-05 23:23:40 | [maml_trainer] epoch #118 | Time 197064.02 s +2025-04-05 23:23:40 | [maml_trainer] epoch #118 | EpochTime 1807.92 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5143 +Average/AverageReturn -51.8767 +Average/Iteration 118 +Average/MaxReturn -44.051 +Average/MinReturn -70.551 +Average/NumEpisodes 120 +Average/StdReturn 4.56661 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9162 +GaussianMLPPolicy/KLAfter 0.00296416 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000172579 +GaussianMLPPolicy/LossBefore -1.22786e-08 +GaussianMLPPolicy/dLoss 0.000172566 +Iteration 118 +MetaTest/Average/AverageDiscountedReturn -51.6935 +MetaTest/Average/AverageReturn -51.6935 +MetaTest/Average/Iteration 118 +MetaTest/Average/MaxReturn -45.7386 +MetaTest/Average/MinReturn -69.3296 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.0934 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6935 +MetaTest/__unnamed_task__/AverageReturn -51.6935 +MetaTest/__unnamed_task__/Iteration 118 +MetaTest/__unnamed_task__/MaxReturn -45.7386 +MetaTest/__unnamed_task__/MinReturn -69.3296 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.0934 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.712e+06 +__unnamed_task__/AverageDiscountedReturn -28.5143 +__unnamed_task__/AverageReturn -51.8767 +__unnamed_task__/Iteration 118 +__unnamed_task__/MaxReturn -44.051 +__unnamed_task__/MinReturn -70.551 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.56661 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-05 23:48:42 | [maml_trainer] epoch #119 | Sampling for adapation and meta-testing... +2025-04-05 23:52:54 | [maml_trainer] epoch #119 | Finished meta-testing... +2025-04-05 23:52:54 | [maml_trainer] epoch #119 | Saving snapshot... +2025-04-05 23:53:16 | [maml_trainer] epoch #119 | Saved +2025-04-05 23:53:16 | [maml_trainer] epoch #119 | Time 198840.84 s +2025-04-05 23:53:16 | [maml_trainer] epoch #119 | EpochTime 1776.82 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4532 +Average/AverageReturn -52.1927 +Average/Iteration 119 +Average/MaxReturn -43.8255 +Average/MinReturn -64.7472 +Average/NumEpisodes 120 +Average/StdReturn 4.74807 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.91263 +GaussianMLPPolicy/KLAfter 0.00329981 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.90919e-05 +GaussianMLPPolicy/LossBefore -5.5631e-09 +GaussianMLPPolicy/dLoss 6.90863e-05 +Iteration 119 +MetaTest/Average/AverageDiscountedReturn -51.2957 +MetaTest/Average/AverageReturn -51.2957 +MetaTest/Average/Iteration 119 +MetaTest/Average/MaxReturn -44.7417 +MetaTest/Average/MinReturn -60.7461 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.13857 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2957 +MetaTest/__unnamed_task__/AverageReturn -51.2957 +MetaTest/__unnamed_task__/Iteration 119 +MetaTest/__unnamed_task__/MaxReturn -44.7417 +MetaTest/__unnamed_task__/MinReturn -60.7461 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.13857 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.76e+06 +__unnamed_task__/AverageDiscountedReturn -28.4532 +__unnamed_task__/AverageReturn -52.1927 +__unnamed_task__/Iteration 119 +__unnamed_task__/MaxReturn -43.8255 +__unnamed_task__/MinReturn -64.7472 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.74807 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 00:18:46 | [maml_trainer] epoch #120 | Sampling for adapation and meta-testing... +2025-04-06 00:22:57 | [maml_trainer] epoch #120 | Finished meta-testing... +2025-04-06 00:22:57 | [maml_trainer] epoch #120 | Saving snapshot... +2025-04-06 00:23:18 | [maml_trainer] epoch #120 | Saved +2025-04-06 00:23:18 | [maml_trainer] epoch #120 | Time 200642.40 s +2025-04-06 00:23:18 | [maml_trainer] epoch #120 | EpochTime 1801.55 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.9677 +Average/AverageReturn -53.003 +Average/Iteration 120 +Average/MaxReturn -43.5648 +Average/MinReturn -72.4551 +Average/NumEpisodes 120 +Average/StdReturn 5.84648 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.9087 +GaussianMLPPolicy/KLAfter 0.00284177 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000106412 +GaussianMLPPolicy/LossBefore -3.85443e-09 +GaussianMLPPolicy/dLoss 0.000106408 +Iteration 120 +MetaTest/Average/AverageDiscountedReturn -50.868 +MetaTest/Average/AverageReturn -50.868 +MetaTest/Average/Iteration 120 +MetaTest/Average/MaxReturn -46.8693 +MetaTest/Average/MinReturn -62.0798 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.45817 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.868 +MetaTest/__unnamed_task__/AverageReturn -50.868 +MetaTest/__unnamed_task__/Iteration 120 +MetaTest/__unnamed_task__/MaxReturn -46.8693 +MetaTest/__unnamed_task__/MinReturn -62.0798 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.45817 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.808e+06 +__unnamed_task__/AverageDiscountedReturn -28.9677 +__unnamed_task__/AverageReturn -53.003 +__unnamed_task__/Iteration 120 +__unnamed_task__/MaxReturn -43.5648 +__unnamed_task__/MinReturn -72.4551 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.84648 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 00:47:16 | [maml_trainer] epoch #121 | Sampling for adapation and meta-testing... +2025-04-06 00:51:11 | [maml_trainer] epoch #121 | Finished meta-testing... +2025-04-06 00:51:11 | [maml_trainer] epoch #121 | Saving snapshot... +2025-04-06 00:51:32 | [maml_trainer] epoch #121 | Saved +2025-04-06 00:51:32 | [maml_trainer] epoch #121 | Time 202336.45 s +2025-04-06 00:51:32 | [maml_trainer] epoch #121 | EpochTime 1694.05 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5768 +Average/AverageReturn -52.1705 +Average/Iteration 121 +Average/MaxReturn -43.4795 +Average/MinReturn -84.6151 +Average/NumEpisodes 120 +Average/StdReturn 6.01891 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.90485 +GaussianMLPPolicy/KLAfter 0.00192267 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.69504e-05 +GaussianMLPPolicy/LossBefore -9.57648e-09 +GaussianMLPPolicy/dLoss -2.696e-05 +Iteration 121 +MetaTest/Average/AverageDiscountedReturn -51.9227 +MetaTest/Average/AverageReturn -51.9227 +MetaTest/Average/Iteration 121 +MetaTest/Average/MaxReturn -44.4324 +MetaTest/Average/MinReturn -72.689 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.4859 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9227 +MetaTest/__unnamed_task__/AverageReturn -51.9227 +MetaTest/__unnamed_task__/Iteration 121 +MetaTest/__unnamed_task__/MaxReturn -44.4324 +MetaTest/__unnamed_task__/MinReturn -72.689 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.4859 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.856e+06 +__unnamed_task__/AverageDiscountedReturn -28.5768 +__unnamed_task__/AverageReturn -52.1705 +__unnamed_task__/Iteration 121 +__unnamed_task__/MaxReturn -43.4795 +__unnamed_task__/MinReturn -84.6151 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.01891 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 01:15:11 | [maml_trainer] epoch #122 | Sampling for adapation and meta-testing... +2025-04-06 01:19:07 | [maml_trainer] epoch #122 | Finished meta-testing... +2025-04-06 01:19:07 | [maml_trainer] epoch #122 | Saving snapshot... +2025-04-06 01:19:28 | [maml_trainer] epoch #122 | Saved +2025-04-06 01:19:28 | [maml_trainer] epoch #122 | Time 204012.66 s +2025-04-06 01:19:28 | [maml_trainer] epoch #122 | EpochTime 1676.21 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3289 +Average/AverageReturn -51.4911 +Average/Iteration 122 +Average/MaxReturn -42.4051 +Average/MinReturn -67.1367 +Average/NumEpisodes 120 +Average/StdReturn 5.06293 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.90069 +GaussianMLPPolicy/KLAfter 0.00209849 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.44951e-05 +GaussianMLPPolicy/LossBefore 5.88099e-09 +GaussianMLPPolicy/dLoss -2.44892e-05 +Iteration 122 +MetaTest/Average/AverageDiscountedReturn -52.3903 +MetaTest/Average/AverageReturn -52.3903 +MetaTest/Average/Iteration 122 +MetaTest/Average/MaxReturn -43.4111 +MetaTest/Average/MinReturn -74.4081 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.81494 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3903 +MetaTest/__unnamed_task__/AverageReturn -52.3903 +MetaTest/__unnamed_task__/Iteration 122 +MetaTest/__unnamed_task__/MaxReturn -43.4111 +MetaTest/__unnamed_task__/MinReturn -74.4081 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.81494 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.904e+06 +__unnamed_task__/AverageDiscountedReturn -28.3289 +__unnamed_task__/AverageReturn -51.4911 +__unnamed_task__/Iteration 122 +__unnamed_task__/MaxReturn -42.4051 +__unnamed_task__/MinReturn -67.1367 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.06293 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 01:43:10 | [maml_trainer] epoch #123 | Sampling for adapation and meta-testing... +2025-04-06 01:47:08 | [maml_trainer] epoch #123 | Finished meta-testing... +2025-04-06 01:47:08 | [maml_trainer] epoch #123 | Saving snapshot... +2025-04-06 01:47:29 | [maml_trainer] epoch #123 | Saved +2025-04-06 01:47:29 | [maml_trainer] epoch #123 | Time 205693.38 s +2025-04-06 01:47:29 | [maml_trainer] epoch #123 | EpochTime 1680.71 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6926 +Average/AverageReturn -52.5528 +Average/Iteration 123 +Average/MaxReturn -42.5225 +Average/MinReturn -76.1241 +Average/NumEpisodes 120 +Average/StdReturn 5.66298 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8962 +GaussianMLPPolicy/KLAfter 0.00164937 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.07604e-05 +GaussianMLPPolicy/LossBefore -2.1855e-09 +GaussianMLPPolicy/dLoss 4.07582e-05 +Iteration 123 +MetaTest/Average/AverageDiscountedReturn -52.0395 +MetaTest/Average/AverageReturn -52.0395 +MetaTest/Average/Iteration 123 +MetaTest/Average/MaxReturn -46.2929 +MetaTest/Average/MinReturn -58.9905 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.07344 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0395 +MetaTest/__unnamed_task__/AverageReturn -52.0395 +MetaTest/__unnamed_task__/Iteration 123 +MetaTest/__unnamed_task__/MaxReturn -46.2929 +MetaTest/__unnamed_task__/MinReturn -58.9905 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.07344 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 5.952e+06 +__unnamed_task__/AverageDiscountedReturn -28.6926 +__unnamed_task__/AverageReturn -52.5528 +__unnamed_task__/Iteration 123 +__unnamed_task__/MaxReturn -42.5225 +__unnamed_task__/MinReturn -76.1241 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.66298 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 02:11:43 | [maml_trainer] epoch #124 | Sampling for adapation and meta-testing... +2025-04-06 02:15:41 | [maml_trainer] epoch #124 | Finished meta-testing... +2025-04-06 02:15:41 | [maml_trainer] epoch #124 | Saving snapshot... +2025-04-06 02:16:02 | [maml_trainer] epoch #124 | Saved +2025-04-06 02:16:02 | [maml_trainer] epoch #124 | Time 207406.38 s +2025-04-06 02:16:02 | [maml_trainer] epoch #124 | EpochTime 1713.01 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.0945 +Average/AverageReturn -53.3447 +Average/Iteration 124 +Average/MaxReturn -43.6329 +Average/MinReturn -76.0709 +Average/NumEpisodes 120 +Average/StdReturn 6.25056 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89201 +GaussianMLPPolicy/KLAfter 0.0040136 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.25575e-05 +GaussianMLPPolicy/LossBefore -3.53654e-09 +GaussianMLPPolicy/dLoss -2.25611e-05 +Iteration 124 +MetaTest/Average/AverageDiscountedReturn -52.2638 +MetaTest/Average/AverageReturn -52.2638 +MetaTest/Average/Iteration 124 +MetaTest/Average/MaxReturn -44.4478 +MetaTest/Average/MinReturn -61.0074 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.57224 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2638 +MetaTest/__unnamed_task__/AverageReturn -52.2638 +MetaTest/__unnamed_task__/Iteration 124 +MetaTest/__unnamed_task__/MaxReturn -44.4478 +MetaTest/__unnamed_task__/MinReturn -61.0074 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.57224 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6e+06 +__unnamed_task__/AverageDiscountedReturn -29.0945 +__unnamed_task__/AverageReturn -53.3447 +__unnamed_task__/Iteration 124 +__unnamed_task__/MaxReturn -43.6329 +__unnamed_task__/MinReturn -76.0709 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.25056 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 02:39:56 | [maml_trainer] epoch #125 | Sampling for adapation and meta-testing... +2025-04-06 02:43:52 | [maml_trainer] epoch #125 | Finished meta-testing... +2025-04-06 02:43:52 | [maml_trainer] epoch #125 | Saving snapshot... +2025-04-06 02:44:14 | [maml_trainer] epoch #125 | Saved +2025-04-06 02:44:14 | [maml_trainer] epoch #125 | Time 209098.12 s +2025-04-06 02:44:14 | [maml_trainer] epoch #125 | EpochTime 1691.73 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8904 +Average/AverageReturn -52.62 +Average/Iteration 125 +Average/MaxReturn -43.582 +Average/MinReturn -72.2481 +Average/NumEpisodes 120 +Average/StdReturn 5.1116 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88925 +GaussianMLPPolicy/KLAfter 0.00373943 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.78723e-06 +GaussianMLPPolicy/LossBefore 3.65575e-09 +GaussianMLPPolicy/dLoss 8.79089e-06 +Iteration 125 +MetaTest/Average/AverageDiscountedReturn -50.8542 +MetaTest/Average/AverageReturn -50.8542 +MetaTest/Average/Iteration 125 +MetaTest/Average/MaxReturn -45.7151 +MetaTest/Average/MinReturn -59.1923 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.82349 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8542 +MetaTest/__unnamed_task__/AverageReturn -50.8542 +MetaTest/__unnamed_task__/Iteration 125 +MetaTest/__unnamed_task__/MaxReturn -45.7151 +MetaTest/__unnamed_task__/MinReturn -59.1923 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.82349 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.048e+06 +__unnamed_task__/AverageDiscountedReturn -28.8904 +__unnamed_task__/AverageReturn -52.62 +__unnamed_task__/Iteration 125 +__unnamed_task__/MaxReturn -43.582 +__unnamed_task__/MinReturn -72.2481 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.1116 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 03:17:35 | [maml_trainer] epoch #126 | Sampling for adapation and meta-testing... +2025-04-06 03:21:35 | [maml_trainer] epoch #126 | Finished meta-testing... +2025-04-06 03:21:35 | [maml_trainer] epoch #126 | Saving snapshot... +2025-04-06 03:21:56 | [maml_trainer] epoch #126 | Saved +2025-04-06 03:21:56 | [maml_trainer] epoch #126 | Time 211360.92 s +2025-04-06 03:21:56 | [maml_trainer] epoch #126 | EpochTime 2262.80 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4678 +Average/AverageReturn -51.316 +Average/Iteration 126 +Average/MaxReturn -42.9172 +Average/MinReturn -66.6647 +Average/NumEpisodes 120 +Average/StdReturn 5.04211 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88772 +GaussianMLPPolicy/KLAfter 0.00370578 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.15805e-05 +GaussianMLPPolicy/LossBefore 1.02123e-08 +GaussianMLPPolicy/dLoss -2.15702e-05 +Iteration 126 +MetaTest/Average/AverageDiscountedReturn -50.9475 +MetaTest/Average/AverageReturn -50.9475 +MetaTest/Average/Iteration 126 +MetaTest/Average/MaxReturn -42.7564 +MetaTest/Average/MinReturn -60.053 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.25355 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9475 +MetaTest/__unnamed_task__/AverageReturn -50.9475 +MetaTest/__unnamed_task__/Iteration 126 +MetaTest/__unnamed_task__/MaxReturn -42.7564 +MetaTest/__unnamed_task__/MinReturn -60.053 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.25355 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.096e+06 +__unnamed_task__/AverageDiscountedReturn -28.4678 +__unnamed_task__/AverageReturn -51.316 +__unnamed_task__/Iteration 126 +__unnamed_task__/MaxReturn -42.9172 +__unnamed_task__/MinReturn -66.6647 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.04211 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 03:45:44 | [maml_trainer] epoch #127 | Sampling for adapation and meta-testing... +2025-04-06 03:49:44 | [maml_trainer] epoch #127 | Finished meta-testing... +2025-04-06 03:49:44 | [maml_trainer] epoch #127 | Saving snapshot... +2025-04-06 03:50:05 | [maml_trainer] epoch #127 | Saved +2025-04-06 03:50:05 | [maml_trainer] epoch #127 | Time 213049.51 s +2025-04-06 03:50:05 | [maml_trainer] epoch #127 | EpochTime 1688.58 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.3878 +Average/AverageReturn -53.5573 +Average/Iteration 127 +Average/MaxReturn -43.469 +Average/MinReturn -81.6421 +Average/NumEpisodes 120 +Average/StdReturn 6.72049 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88698 +GaussianMLPPolicy/KLAfter 0.00363361 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000108189 +GaussianMLPPolicy/LossBefore 2.22524e-09 +GaussianMLPPolicy/dLoss 0.000108191 +Iteration 127 +MetaTest/Average/AverageDiscountedReturn -54.1332 +MetaTest/Average/AverageReturn -54.1332 +MetaTest/Average/Iteration 127 +MetaTest/Average/MaxReturn -45.5398 +MetaTest/Average/MinReturn -125.32 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.7397 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1332 +MetaTest/__unnamed_task__/AverageReturn -54.1332 +MetaTest/__unnamed_task__/Iteration 127 +MetaTest/__unnamed_task__/MaxReturn -45.5398 +MetaTest/__unnamed_task__/MinReturn -125.32 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.7397 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.144e+06 +__unnamed_task__/AverageDiscountedReturn -29.3878 +__unnamed_task__/AverageReturn -53.5573 +__unnamed_task__/Iteration 127 +__unnamed_task__/MaxReturn -43.469 +__unnamed_task__/MinReturn -81.6421 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.72049 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 04:13:38 | [maml_trainer] epoch #128 | Sampling for adapation and meta-testing... +2025-04-06 04:17:34 | [maml_trainer] epoch #128 | Finished meta-testing... +2025-04-06 04:17:34 | [maml_trainer] epoch #128 | Saving snapshot... +2025-04-06 04:17:55 | [maml_trainer] epoch #128 | Saved +2025-04-06 04:17:55 | [maml_trainer] epoch #128 | Time 214719.86 s +2025-04-06 04:17:55 | [maml_trainer] epoch #128 | EpochTime 1670.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8438 +Average/AverageReturn -52.46 +Average/Iteration 128 +Average/MaxReturn -42.929 +Average/MinReturn -77.9564 +Average/NumEpisodes 120 +Average/StdReturn 7.01241 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88796 +GaussianMLPPolicy/KLAfter 0.00581481 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.4963e-05 +GaussianMLPPolicy/LossBefore 9.13938e-10 +GaussianMLPPolicy/dLoss 2.49639e-05 +Iteration 128 +MetaTest/Average/AverageDiscountedReturn -52.6662 +MetaTest/Average/AverageReturn -52.6662 +MetaTest/Average/Iteration 128 +MetaTest/Average/MaxReturn -42.3193 +MetaTest/Average/MinReturn -76.1263 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.15018 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6662 +MetaTest/__unnamed_task__/AverageReturn -52.6662 +MetaTest/__unnamed_task__/Iteration 128 +MetaTest/__unnamed_task__/MaxReturn -42.3193 +MetaTest/__unnamed_task__/MinReturn -76.1263 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.15018 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.192e+06 +__unnamed_task__/AverageDiscountedReturn -28.8438 +__unnamed_task__/AverageReturn -52.46 +__unnamed_task__/Iteration 128 +__unnamed_task__/MaxReturn -42.929 +__unnamed_task__/MinReturn -77.9564 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.01241 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 04:41:30 | [maml_trainer] epoch #129 | Sampling for adapation and meta-testing... +2025-04-06 04:45:29 | [maml_trainer] epoch #129 | Finished meta-testing... +2025-04-06 04:45:29 | [maml_trainer] epoch #129 | Saving snapshot... +2025-04-06 04:45:50 | [maml_trainer] epoch #129 | Saved +2025-04-06 04:45:50 | [maml_trainer] epoch #129 | Time 216394.02 s +2025-04-06 04:45:50 | [maml_trainer] epoch #129 | EpochTime 1674.15 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.349 +Average/AverageReturn -50.8814 +Average/Iteration 129 +Average/MaxReturn -42.1891 +Average/MinReturn -88.7122 +Average/NumEpisodes 120 +Average/StdReturn 6.6739 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88884 +GaussianMLPPolicy/KLAfter 0.00572082 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000205013 +GaussianMLPPolicy/LossBefore 1.62919e-09 +GaussianMLPPolicy/dLoss -0.000205012 +Iteration 129 +MetaTest/Average/AverageDiscountedReturn -50.4784 +MetaTest/Average/AverageReturn -50.4784 +MetaTest/Average/Iteration 129 +MetaTest/Average/MaxReturn -44.2467 +MetaTest/Average/MinReturn -69.3468 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.58445 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4784 +MetaTest/__unnamed_task__/AverageReturn -50.4784 +MetaTest/__unnamed_task__/Iteration 129 +MetaTest/__unnamed_task__/MaxReturn -44.2467 +MetaTest/__unnamed_task__/MinReturn -69.3468 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.58445 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.24e+06 +__unnamed_task__/AverageDiscountedReturn -28.349 +__unnamed_task__/AverageReturn -50.8814 +__unnamed_task__/Iteration 129 +__unnamed_task__/MaxReturn -42.1891 +__unnamed_task__/MinReturn -88.7122 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.6739 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 05:09:19 | [maml_trainer] epoch #130 | Sampling for adapation and meta-testing... +2025-04-06 05:13:11 | [maml_trainer] epoch #130 | Finished meta-testing... +2025-04-06 05:13:11 | [maml_trainer] epoch #130 | Saving snapshot... +2025-04-06 05:13:32 | [maml_trainer] epoch #130 | Saved +2025-04-06 05:13:32 | [maml_trainer] epoch #130 | Time 218056.93 s +2025-04-06 05:13:32 | [maml_trainer] epoch #130 | EpochTime 1662.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9318 +Average/AverageReturn -52.5828 +Average/Iteration 130 +Average/MaxReturn -40.5446 +Average/MinReturn -104.403 +Average/NumEpisodes 120 +Average/StdReturn 9.1081 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88833 +GaussianMLPPolicy/KLAfter 0.00383478 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.83886e-05 +GaussianMLPPolicy/LossBefore 1.4027e-08 +GaussianMLPPolicy/dLoss 7.84027e-05 +Iteration 130 +MetaTest/Average/AverageDiscountedReturn -48.9587 +MetaTest/Average/AverageReturn -48.9587 +MetaTest/Average/Iteration 130 +MetaTest/Average/MaxReturn -41.0706 +MetaTest/Average/MinReturn -60.1262 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.50735 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9587 +MetaTest/__unnamed_task__/AverageReturn -48.9587 +MetaTest/__unnamed_task__/Iteration 130 +MetaTest/__unnamed_task__/MaxReturn -41.0706 +MetaTest/__unnamed_task__/MinReturn -60.1262 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.50735 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.288e+06 +__unnamed_task__/AverageDiscountedReturn -28.9318 +__unnamed_task__/AverageReturn -52.5828 +__unnamed_task__/Iteration 130 +__unnamed_task__/MaxReturn -40.5446 +__unnamed_task__/MinReturn -104.403 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.1081 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 05:37:12 | [maml_trainer] epoch #131 | Sampling for adapation and meta-testing... +2025-04-06 05:41:15 | [maml_trainer] epoch #131 | Finished meta-testing... +2025-04-06 05:41:15 | [maml_trainer] epoch #131 | Saving snapshot... +2025-04-06 05:41:36 | [maml_trainer] epoch #131 | Saved +2025-04-06 05:41:36 | [maml_trainer] epoch #131 | Time 219740.81 s +2025-04-06 05:41:36 | [maml_trainer] epoch #131 | EpochTime 1683.87 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.791 +Average/AverageReturn -52.2391 +Average/Iteration 131 +Average/MaxReturn -42.2452 +Average/MinReturn -107.358 +Average/NumEpisodes 120 +Average/StdReturn 9.3302 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88794 +GaussianMLPPolicy/KLAfter 0.00310472 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.35227e-05 +GaussianMLPPolicy/LossBefore 5.28494e-09 +GaussianMLPPolicy/dLoss 6.3528e-05 +Iteration 131 +MetaTest/Average/AverageDiscountedReturn -53.8318 +MetaTest/Average/AverageReturn -53.8318 +MetaTest/Average/Iteration 131 +MetaTest/Average/MaxReturn -41.1707 +MetaTest/Average/MinReturn -84.4594 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.35483 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8318 +MetaTest/__unnamed_task__/AverageReturn -53.8318 +MetaTest/__unnamed_task__/Iteration 131 +MetaTest/__unnamed_task__/MaxReturn -41.1707 +MetaTest/__unnamed_task__/MinReturn -84.4594 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.35483 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.336e+06 +__unnamed_task__/AverageDiscountedReturn -28.791 +__unnamed_task__/AverageReturn -52.2391 +__unnamed_task__/Iteration 131 +__unnamed_task__/MaxReturn -42.2452 +__unnamed_task__/MinReturn -107.358 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.3302 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 06:05:26 | [maml_trainer] epoch #132 | Sampling for adapation and meta-testing... +2025-04-06 06:09:22 | [maml_trainer] epoch #132 | Finished meta-testing... +2025-04-06 06:09:22 | [maml_trainer] epoch #132 | Saving snapshot... +2025-04-06 06:09:43 | [maml_trainer] epoch #132 | Saved +2025-04-06 06:09:43 | [maml_trainer] epoch #132 | Time 221427.27 s +2025-04-06 06:09:43 | [maml_trainer] epoch #132 | EpochTime 1686.46 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.5316 +Average/AverageReturn -56.7547 +Average/Iteration 132 +Average/MaxReturn -41.3266 +Average/MinReturn -150.326 +Average/NumEpisodes 120 +Average/StdReturn 20.1539 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88789 +GaussianMLPPolicy/KLAfter 0.00250488 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.3088e-05 +GaussianMLPPolicy/LossBefore -5.5631e-09 +GaussianMLPPolicy/dLoss -2.30935e-05 +Iteration 132 +MetaTest/Average/AverageDiscountedReturn -49.8728 +MetaTest/Average/AverageReturn -49.8728 +MetaTest/Average/Iteration 132 +MetaTest/Average/MaxReturn -41.5658 +MetaTest/Average/MinReturn -59.4331 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.01566 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8728 +MetaTest/__unnamed_task__/AverageReturn -49.8728 +MetaTest/__unnamed_task__/Iteration 132 +MetaTest/__unnamed_task__/MaxReturn -41.5658 +MetaTest/__unnamed_task__/MinReturn -59.4331 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.01566 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.384e+06 +__unnamed_task__/AverageDiscountedReturn -29.5316 +__unnamed_task__/AverageReturn -56.7547 +__unnamed_task__/Iteration 132 +__unnamed_task__/MaxReturn -41.3266 +__unnamed_task__/MinReturn -150.326 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.1539 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 06:33:30 | [maml_trainer] epoch #133 | Sampling for adapation and meta-testing... +2025-04-06 06:37:24 | [maml_trainer] epoch #133 | Finished meta-testing... +2025-04-06 06:37:24 | [maml_trainer] epoch #133 | Saving snapshot... +2025-04-06 06:37:46 | [maml_trainer] epoch #133 | Saved +2025-04-06 06:37:46 | [maml_trainer] epoch #133 | Time 223110.00 s +2025-04-06 06:37:46 | [maml_trainer] epoch #133 | EpochTime 1682.73 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.6824 +Average/AverageReturn -57.2107 +Average/Iteration 133 +Average/MaxReturn -28.5136 +Average/MinReturn -176.403 +Average/NumEpisodes 120 +Average/StdReturn 24.4825 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88734 +GaussianMLPPolicy/KLAfter 0.00364025 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000123101 +GaussianMLPPolicy/LossBefore -3.27826e-09 +GaussianMLPPolicy/dLoss -0.000123105 +Iteration 133 +MetaTest/Average/AverageDiscountedReturn -55.7915 +MetaTest/Average/AverageReturn -55.7915 +MetaTest/Average/Iteration 133 +MetaTest/Average/MaxReturn -40.8413 +MetaTest/Average/MinReturn -173.51 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 27.5039 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.7915 +MetaTest/__unnamed_task__/AverageReturn -55.7915 +MetaTest/__unnamed_task__/Iteration 133 +MetaTest/__unnamed_task__/MaxReturn -40.8413 +MetaTest/__unnamed_task__/MinReturn -173.51 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 27.5039 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.432e+06 +__unnamed_task__/AverageDiscountedReturn -29.6824 +__unnamed_task__/AverageReturn -57.2107 +__unnamed_task__/Iteration 133 +__unnamed_task__/MaxReturn -28.5136 +__unnamed_task__/MinReturn -176.403 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 24.4825 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 07:01:44 | [maml_trainer] epoch #134 | Sampling for adapation and meta-testing... +2025-04-06 07:05:39 | [maml_trainer] epoch #134 | Finished meta-testing... +2025-04-06 07:05:39 | [maml_trainer] epoch #134 | Saving snapshot... +2025-04-06 07:06:00 | [maml_trainer] epoch #134 | Saved +2025-04-06 07:06:00 | [maml_trainer] epoch #134 | Time 224804.62 s +2025-04-06 07:06:00 | [maml_trainer] epoch #134 | EpochTime 1694.62 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.2732 +Average/AverageReturn -55.6752 +Average/Iteration 134 +Average/MaxReturn -41.0252 +Average/MinReturn -169.621 +Average/NumEpisodes 120 +Average/StdReturn 20.2712 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88678 +GaussianMLPPolicy/KLAfter 0.00538287 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.60329e-06 +GaussianMLPPolicy/LossBefore 3.53654e-09 +GaussianMLPPolicy/dLoss -7.59975e-06 +Iteration 134 +MetaTest/Average/AverageDiscountedReturn -57.9552 +MetaTest/Average/AverageReturn -57.9552 +MetaTest/Average/Iteration 134 +MetaTest/Average/MaxReturn -45.0538 +MetaTest/Average/MinReturn -120.916 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 19.9562 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.9552 +MetaTest/__unnamed_task__/AverageReturn -57.9552 +MetaTest/__unnamed_task__/Iteration 134 +MetaTest/__unnamed_task__/MaxReturn -45.0538 +MetaTest/__unnamed_task__/MinReturn -120.916 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 19.9562 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.48e+06 +__unnamed_task__/AverageDiscountedReturn -29.2732 +__unnamed_task__/AverageReturn -55.6752 +__unnamed_task__/Iteration 134 +__unnamed_task__/MaxReturn -41.0252 +__unnamed_task__/MinReturn -169.621 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.2712 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 07:29:37 | [maml_trainer] epoch #135 | Sampling for adapation and meta-testing... +2025-04-06 07:33:31 | [maml_trainer] epoch #135 | Finished meta-testing... +2025-04-06 07:33:31 | [maml_trainer] epoch #135 | Saving snapshot... +2025-04-06 07:33:52 | [maml_trainer] epoch #135 | Saved +2025-04-06 07:33:52 | [maml_trainer] epoch #135 | Time 226476.20 s +2025-04-06 07:33:52 | [maml_trainer] epoch #135 | EpochTime 1671.57 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.6109 +Average/AverageReturn -57.2685 +Average/Iteration 135 +Average/MaxReturn 234.041 +Average/MinReturn -178.707 +Average/NumEpisodes 120 +Average/StdReturn 37.3713 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88653 +GaussianMLPPolicy/KLAfter 0.00431025 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.6709e-05 +GaussianMLPPolicy/LossBefore -8.29498e-10 +GaussianMLPPolicy/dLoss -1.67098e-05 +Iteration 135 +MetaTest/Average/AverageDiscountedReturn -56.3143 +MetaTest/Average/AverageReturn -56.3143 +MetaTest/Average/Iteration 135 +MetaTest/Average/MaxReturn -43.2209 +MetaTest/Average/MinReturn -137.745 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 20.0515 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.3143 +MetaTest/__unnamed_task__/AverageReturn -56.3143 +MetaTest/__unnamed_task__/Iteration 135 +MetaTest/__unnamed_task__/MaxReturn -43.2209 +MetaTest/__unnamed_task__/MinReturn -137.745 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 20.0515 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.528e+06 +__unnamed_task__/AverageDiscountedReturn -29.6109 +__unnamed_task__/AverageReturn -57.2685 +__unnamed_task__/Iteration 135 +__unnamed_task__/MaxReturn 234.041 +__unnamed_task__/MinReturn -178.707 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 37.3713 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 07:57:26 | [maml_trainer] epoch #136 | Sampling for adapation and meta-testing... +2025-04-06 08:01:25 | [maml_trainer] epoch #136 | Finished meta-testing... +2025-04-06 08:01:25 | [maml_trainer] epoch #136 | Saving snapshot... +2025-04-06 08:01:47 | [maml_trainer] epoch #136 | Saved +2025-04-06 08:01:47 | [maml_trainer] epoch #136 | Time 228151.04 s +2025-04-06 08:01:47 | [maml_trainer] epoch #136 | EpochTime 1674.84 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.3952 +Average/AverageReturn -58.7606 +Average/Iteration 136 +Average/MaxReturn 140.105 +Average/MinReturn -180.749 +Average/NumEpisodes 120 +Average/StdReturn 31.7974 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8876 +GaussianMLPPolicy/KLAfter 0.00267749 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.20986e-05 +GaussianMLPPolicy/LossBefore -5.26508e-10 +GaussianMLPPolicy/dLoss 1.20981e-05 +Iteration 136 +MetaTest/Average/AverageDiscountedReturn -45.8903 +MetaTest/Average/AverageReturn -45.8903 +MetaTest/Average/Iteration 136 +MetaTest/Average/MaxReturn 131.726 +MetaTest/Average/MinReturn -166.301 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 48.4294 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8903 +MetaTest/__unnamed_task__/AverageReturn -45.8903 +MetaTest/__unnamed_task__/Iteration 136 +MetaTest/__unnamed_task__/MaxReturn 131.726 +MetaTest/__unnamed_task__/MinReturn -166.301 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 48.4294 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.576e+06 +__unnamed_task__/AverageDiscountedReturn -30.3952 +__unnamed_task__/AverageReturn -58.7606 +__unnamed_task__/Iteration 136 +__unnamed_task__/MaxReturn 140.105 +__unnamed_task__/MinReturn -180.749 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 31.7974 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 08:25:27 | [maml_trainer] epoch #137 | Sampling for adapation and meta-testing... +2025-04-06 08:29:29 | [maml_trainer] epoch #137 | Finished meta-testing... +2025-04-06 08:29:29 | [maml_trainer] epoch #137 | Saving snapshot... +2025-04-06 08:29:50 | [maml_trainer] epoch #137 | Saved +2025-04-06 08:29:50 | [maml_trainer] epoch #137 | Time 229834.56 s +2025-04-06 08:29:50 | [maml_trainer] epoch #137 | EpochTime 1683.52 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.7801 +Average/AverageReturn -56.0983 +Average/Iteration 137 +Average/MaxReturn 22.1 +Average/MinReturn -150.718 +Average/NumEpisodes 120 +Average/StdReturn 22.9984 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88904 +GaussianMLPPolicy/KLAfter 0.00289323 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.21982e-06 +GaussianMLPPolicy/LossBefore 1.17222e-09 +GaussianMLPPolicy/dLoss 3.221e-06 +Iteration 137 +MetaTest/Average/AverageDiscountedReturn -55.2808 +MetaTest/Average/AverageReturn -55.2808 +MetaTest/Average/Iteration 137 +MetaTest/Average/MaxReturn -37.0179 +MetaTest/Average/MinReturn -106.023 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.2516 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.2808 +MetaTest/__unnamed_task__/AverageReturn -55.2808 +MetaTest/__unnamed_task__/Iteration 137 +MetaTest/__unnamed_task__/MaxReturn -37.0179 +MetaTest/__unnamed_task__/MinReturn -106.023 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.2516 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.624e+06 +__unnamed_task__/AverageDiscountedReturn -29.7801 +__unnamed_task__/AverageReturn -56.0983 +__unnamed_task__/Iteration 137 +__unnamed_task__/MaxReturn 22.1 +__unnamed_task__/MinReturn -150.718 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 22.9984 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 08:53:33 | [maml_trainer] epoch #138 | Sampling for adapation and meta-testing... +2025-04-06 08:57:31 | [maml_trainer] epoch #138 | Finished meta-testing... +2025-04-06 08:57:31 | [maml_trainer] epoch #138 | Saving snapshot... +2025-04-06 08:57:52 | [maml_trainer] epoch #138 | Saved +2025-04-06 08:57:52 | [maml_trainer] epoch #138 | Time 231516.64 s +2025-04-06 08:57:52 | [maml_trainer] epoch #138 | EpochTime 1682.07 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.0717 +Average/AverageReturn -57.4925 +Average/Iteration 138 +Average/MaxReturn 114.852 +Average/MinReturn -164.737 +Average/NumEpisodes 120 +Average/StdReturn 28.7014 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89107 +GaussianMLPPolicy/KLAfter 0.00313304 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.31558e-05 +GaussianMLPPolicy/LossBefore -2.45372e-09 +GaussianMLPPolicy/dLoss -2.31583e-05 +Iteration 138 +MetaTest/Average/AverageDiscountedReturn -54.9232 +MetaTest/Average/AverageReturn -54.9232 +MetaTest/Average/Iteration 138 +MetaTest/Average/MaxReturn -42.9758 +MetaTest/Average/MinReturn -86.2242 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.0307 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.9232 +MetaTest/__unnamed_task__/AverageReturn -54.9232 +MetaTest/__unnamed_task__/Iteration 138 +MetaTest/__unnamed_task__/MaxReturn -42.9758 +MetaTest/__unnamed_task__/MinReturn -86.2242 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.0307 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.672e+06 +__unnamed_task__/AverageDiscountedReturn -30.0717 +__unnamed_task__/AverageReturn -57.4925 +__unnamed_task__/Iteration 138 +__unnamed_task__/MaxReturn 114.852 +__unnamed_task__/MinReturn -164.737 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 28.7014 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 09:21:42 | [maml_trainer] epoch #139 | Sampling for adapation and meta-testing... +2025-04-06 09:25:41 | [maml_trainer] epoch #139 | Finished meta-testing... +2025-04-06 09:25:41 | [maml_trainer] epoch #139 | Saving snapshot... +2025-04-06 09:26:02 | [maml_trainer] epoch #139 | Saved +2025-04-06 09:26:02 | [maml_trainer] epoch #139 | Time 233206.36 s +2025-04-06 09:26:02 | [maml_trainer] epoch #139 | EpochTime 1689.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.9594 +Average/AverageReturn -55.9177 +Average/Iteration 139 +Average/MaxReturn -42.0633 +Average/MinReturn -158.054 +Average/NumEpisodes 120 +Average/StdReturn 15.841 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89405 +GaussianMLPPolicy/KLAfter 0.00373776 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.68601e-05 +GaussianMLPPolicy/LossBefore 9.35793e-09 +GaussianMLPPolicy/dLoss -4.68507e-05 +Iteration 139 +MetaTest/Average/AverageDiscountedReturn -52.0098 +MetaTest/Average/AverageReturn -52.0098 +MetaTest/Average/Iteration 139 +MetaTest/Average/MaxReturn -43.7705 +MetaTest/Average/MinReturn -67.4596 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.78129 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0098 +MetaTest/__unnamed_task__/AverageReturn -52.0098 +MetaTest/__unnamed_task__/Iteration 139 +MetaTest/__unnamed_task__/MaxReturn -43.7705 +MetaTest/__unnamed_task__/MinReturn -67.4596 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.78129 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.72e+06 +__unnamed_task__/AverageDiscountedReturn -29.9594 +__unnamed_task__/AverageReturn -55.9177 +__unnamed_task__/Iteration 139 +__unnamed_task__/MaxReturn -42.0633 +__unnamed_task__/MinReturn -158.054 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.841 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 09:49:54 | [maml_trainer] epoch #140 | Sampling for adapation and meta-testing... +2025-04-06 09:53:54 | [maml_trainer] epoch #140 | Finished meta-testing... +2025-04-06 09:53:54 | [maml_trainer] epoch #140 | Saving snapshot... +2025-04-06 09:54:15 | [maml_trainer] epoch #140 | Saved +2025-04-06 09:54:15 | [maml_trainer] epoch #140 | Time 234899.87 s +2025-04-06 09:54:15 | [maml_trainer] epoch #140 | EpochTime 1693.51 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9261 +Average/AverageReturn -51.4228 +Average/Iteration 140 +Average/MaxReturn 231.9 +Average/MinReturn -162.324 +Average/NumEpisodes 120 +Average/StdReturn 30.0854 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89457 +GaussianMLPPolicy/KLAfter 0.0033877 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.77536e-05 +GaussianMLPPolicy/LossBefore -3.13918e-09 +GaussianMLPPolicy/dLoss 1.77505e-05 +Iteration 140 +MetaTest/Average/AverageDiscountedReturn -53.8918 +MetaTest/Average/AverageReturn -53.8918 +MetaTest/Average/Iteration 140 +MetaTest/Average/MaxReturn -44.7785 +MetaTest/Average/MinReturn -68.6761 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.0788 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8918 +MetaTest/__unnamed_task__/AverageReturn -53.8918 +MetaTest/__unnamed_task__/Iteration 140 +MetaTest/__unnamed_task__/MaxReturn -44.7785 +MetaTest/__unnamed_task__/MinReturn -68.6761 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.0788 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.768e+06 +__unnamed_task__/AverageDiscountedReturn -28.9261 +__unnamed_task__/AverageReturn -51.4228 +__unnamed_task__/Iteration 140 +__unnamed_task__/MaxReturn 231.9 +__unnamed_task__/MinReturn -162.324 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 30.0854 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 10:18:06 | [maml_trainer] epoch #141 | Sampling for adapation and meta-testing... +2025-04-06 10:22:01 | [maml_trainer] epoch #141 | Finished meta-testing... +2025-04-06 10:22:01 | [maml_trainer] epoch #141 | Saving snapshot... +2025-04-06 10:22:22 | [maml_trainer] epoch #141 | Saved +2025-04-06 10:22:22 | [maml_trainer] epoch #141 | Time 236586.86 s +2025-04-06 10:22:22 | [maml_trainer] epoch #141 | EpochTime 1686.99 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.2379 +Average/AverageReturn -52.0956 +Average/Iteration 141 +Average/MaxReturn -40.8622 +Average/MinReturn -76.5301 +Average/NumEpisodes 120 +Average/StdReturn 5.99735 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89478 +GaussianMLPPolicy/KLAfter 0.00182271 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.65648e-05 +GaussianMLPPolicy/LossBefore -1.70867e-09 +GaussianMLPPolicy/dLoss -3.65665e-05 +Iteration 141 +MetaTest/Average/AverageDiscountedReturn -53.7784 +MetaTest/Average/AverageReturn -53.7784 +MetaTest/Average/Iteration 141 +MetaTest/Average/MaxReturn -43.3935 +MetaTest/Average/MinReturn -69.8166 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.62944 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.7784 +MetaTest/__unnamed_task__/AverageReturn -53.7784 +MetaTest/__unnamed_task__/Iteration 141 +MetaTest/__unnamed_task__/MaxReturn -43.3935 +MetaTest/__unnamed_task__/MinReturn -69.8166 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.62944 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.816e+06 +__unnamed_task__/AverageDiscountedReturn -29.2379 +__unnamed_task__/AverageReturn -52.0956 +__unnamed_task__/Iteration 141 +__unnamed_task__/MaxReturn -40.8622 +__unnamed_task__/MinReturn -76.5301 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.99735 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 10:46:10 | [maml_trainer] epoch #142 | Sampling for adapation and meta-testing... +2025-04-06 10:50:20 | [maml_trainer] epoch #142 | Finished meta-testing... +2025-04-06 10:50:20 | [maml_trainer] epoch #142 | Saving snapshot... +2025-04-06 10:50:43 | [maml_trainer] epoch #142 | Saved +2025-04-06 10:50:43 | [maml_trainer] epoch #142 | Time 238287.41 s +2025-04-06 10:50:43 | [maml_trainer] epoch #142 | EpochTime 1700.55 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.7505 +Average/AverageReturn -52.3682 +Average/Iteration 142 +Average/MaxReturn 218.358 +Average/MinReturn -104.756 +Average/NumEpisodes 120 +Average/StdReturn 26.3006 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89542 +GaussianMLPPolicy/KLAfter 0.00143578 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.33688e-05 +GaussianMLPPolicy/LossBefore -1.40071e-09 +GaussianMLPPolicy/dLoss 4.33674e-05 +Iteration 142 +MetaTest/Average/AverageDiscountedReturn -53.5468 +MetaTest/Average/AverageReturn -53.5468 +MetaTest/Average/Iteration 142 +MetaTest/Average/MaxReturn -45.0243 +MetaTest/Average/MinReturn -64.6852 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.65446 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5468 +MetaTest/__unnamed_task__/AverageReturn -53.5468 +MetaTest/__unnamed_task__/Iteration 142 +MetaTest/__unnamed_task__/MaxReturn -45.0243 +MetaTest/__unnamed_task__/MinReturn -64.6852 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.65446 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.864e+06 +__unnamed_task__/AverageDiscountedReturn -29.7505 +__unnamed_task__/AverageReturn -52.3682 +__unnamed_task__/Iteration 142 +__unnamed_task__/MaxReturn 218.358 +__unnamed_task__/MinReturn -104.756 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.3006 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 11:15:36 | [maml_trainer] epoch #143 | Sampling for adapation and meta-testing... +2025-04-06 11:19:45 | [maml_trainer] epoch #143 | Finished meta-testing... +2025-04-06 11:19:45 | [maml_trainer] epoch #143 | Saving snapshot... +2025-04-06 11:20:07 | [maml_trainer] epoch #143 | Saved +2025-04-06 11:20:07 | [maml_trainer] epoch #143 | Time 240051.94 s +2025-04-06 11:20:07 | [maml_trainer] epoch #143 | EpochTime 1764.52 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.2891 +Average/AverageReturn -51.3183 +Average/Iteration 143 +Average/MaxReturn 158.153 +Average/MinReturn -74.0797 +Average/NumEpisodes 120 +Average/StdReturn 20.4606 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89533 +GaussianMLPPolicy/KLAfter 0.00147648 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.61075e-06 +GaussianMLPPolicy/LossBefore 2.38419e-10 +GaussianMLPPolicy/dLoss 3.61099e-06 +Iteration 143 +MetaTest/Average/AverageDiscountedReturn -42.2709 +MetaTest/Average/AverageReturn -42.2709 +MetaTest/Average/Iteration 143 +MetaTest/Average/MaxReturn 206.019 +MetaTest/Average/MinReturn -80.0761 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 57.4072 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -42.2709 +MetaTest/__unnamed_task__/AverageReturn -42.2709 +MetaTest/__unnamed_task__/Iteration 143 +MetaTest/__unnamed_task__/MaxReturn 206.019 +MetaTest/__unnamed_task__/MinReturn -80.0761 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 57.4072 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.912e+06 +__unnamed_task__/AverageDiscountedReturn -29.2891 +__unnamed_task__/AverageReturn -51.3183 +__unnamed_task__/Iteration 143 +__unnamed_task__/MaxReturn 158.153 +__unnamed_task__/MinReturn -74.0797 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.4606 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 11:45:04 | [maml_trainer] epoch #144 | Sampling for adapation and meta-testing... +2025-04-06 11:49:14 | [maml_trainer] epoch #144 | Finished meta-testing... +2025-04-06 11:49:14 | [maml_trainer] epoch #144 | Saving snapshot... +2025-04-06 11:49:37 | [maml_trainer] epoch #144 | Saved +2025-04-06 11:49:37 | [maml_trainer] epoch #144 | Time 241821.73 s +2025-04-06 11:49:37 | [maml_trainer] epoch #144 | EpochTime 1769.78 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.1772 +Average/AverageReturn -55.2764 +Average/Iteration 144 +Average/MaxReturn -43.4226 +Average/MinReturn -81.9317 +Average/NumEpisodes 120 +Average/StdReturn 7.84737 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89504 +GaussianMLPPolicy/KLAfter 0.00196751 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.7935e-05 +GaussianMLPPolicy/LossBefore -1.54972e-09 +GaussianMLPPolicy/dLoss -4.79365e-05 +Iteration 144 +MetaTest/Average/AverageDiscountedReturn -52.6577 +MetaTest/Average/AverageReturn -52.6577 +MetaTest/Average/Iteration 144 +MetaTest/Average/MaxReturn -44.2471 +MetaTest/Average/MinReturn -69.3337 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.43583 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6577 +MetaTest/__unnamed_task__/AverageReturn -52.6577 +MetaTest/__unnamed_task__/Iteration 144 +MetaTest/__unnamed_task__/MaxReturn -44.2471 +MetaTest/__unnamed_task__/MinReturn -69.3337 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.43583 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 6.96e+06 +__unnamed_task__/AverageDiscountedReturn -30.1772 +__unnamed_task__/AverageReturn -55.2764 +__unnamed_task__/Iteration 144 +__unnamed_task__/MaxReturn -43.4226 +__unnamed_task__/MinReturn -81.9317 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.84737 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 12:14:21 | [maml_trainer] epoch #145 | Sampling for adapation and meta-testing... +2025-04-06 12:18:32 | [maml_trainer] epoch #145 | Finished meta-testing... +2025-04-06 12:18:32 | [maml_trainer] epoch #145 | Saving snapshot... +2025-04-06 12:18:56 | [maml_trainer] epoch #145 | Saved +2025-04-06 12:18:56 | [maml_trainer] epoch #145 | Time 243580.01 s +2025-04-06 12:18:56 | [maml_trainer] epoch #145 | EpochTime 1758.28 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.7638 +Average/AverageReturn -53.4969 +Average/Iteration 145 +Average/MaxReturn -44.0326 +Average/MinReturn -83.5896 +Average/NumEpisodes 120 +Average/StdReturn 6.54722 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89462 +GaussianMLPPolicy/KLAfter 0.00214007 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000100051 +GaussianMLPPolicy/LossBefore 2.03848e-08 +GaussianMLPPolicy/dLoss -0.000100031 +Iteration 145 +MetaTest/Average/AverageDiscountedReturn -53.5376 +MetaTest/Average/AverageReturn -53.5376 +MetaTest/Average/Iteration 145 +MetaTest/Average/MaxReturn -44.945 +MetaTest/Average/MinReturn -65.1307 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.26743 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.5376 +MetaTest/__unnamed_task__/AverageReturn -53.5376 +MetaTest/__unnamed_task__/Iteration 145 +MetaTest/__unnamed_task__/MaxReturn -44.945 +MetaTest/__unnamed_task__/MinReturn -65.1307 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.26743 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.008e+06 +__unnamed_task__/AverageDiscountedReturn -29.7638 +__unnamed_task__/AverageReturn -53.4969 +__unnamed_task__/Iteration 145 +__unnamed_task__/MaxReturn -44.0326 +__unnamed_task__/MinReturn -83.5896 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.54722 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 12:43:36 | [maml_trainer] epoch #146 | Sampling for adapation and meta-testing... +2025-04-06 12:47:41 | [maml_trainer] epoch #146 | Finished meta-testing... +2025-04-06 12:47:41 | [maml_trainer] epoch #146 | Saving snapshot... +2025-04-06 12:48:04 | [maml_trainer] epoch #146 | Saved +2025-04-06 12:48:04 | [maml_trainer] epoch #146 | Time 245328.43 s +2025-04-06 12:48:04 | [maml_trainer] epoch #146 | EpochTime 1748.41 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.8033 +Average/AverageReturn -54.0422 +Average/Iteration 146 +Average/MaxReturn -40.2827 +Average/MinReturn -134.087 +Average/NumEpisodes 120 +Average/StdReturn 9.69861 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89443 +GaussianMLPPolicy/KLAfter 0.00103609 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.51266e-05 +GaussianMLPPolicy/LossBefore 3.01997e-09 +GaussianMLPPolicy/dLoss 1.51296e-05 +Iteration 146 +MetaTest/Average/AverageDiscountedReturn -53.0162 +MetaTest/Average/AverageReturn -53.0162 +MetaTest/Average/Iteration 146 +MetaTest/Average/MaxReturn -45.6584 +MetaTest/Average/MinReturn -86.8615 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.80968 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0162 +MetaTest/__unnamed_task__/AverageReturn -53.0162 +MetaTest/__unnamed_task__/Iteration 146 +MetaTest/__unnamed_task__/MaxReturn -45.6584 +MetaTest/__unnamed_task__/MinReturn -86.8615 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.80968 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.056e+06 +__unnamed_task__/AverageDiscountedReturn -29.8033 +__unnamed_task__/AverageReturn -54.0422 +__unnamed_task__/Iteration 146 +__unnamed_task__/MaxReturn -40.2827 +__unnamed_task__/MinReturn -134.087 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.69861 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 13:13:02 | [maml_trainer] epoch #147 | Sampling for adapation and meta-testing... +2025-04-06 13:17:07 | [maml_trainer] epoch #147 | Finished meta-testing... +2025-04-06 13:17:07 | [maml_trainer] epoch #147 | Saving snapshot... +2025-04-06 13:17:31 | [maml_trainer] epoch #147 | Saved +2025-04-06 13:17:31 | [maml_trainer] epoch #147 | Time 247095.05 s +2025-04-06 13:17:31 | [maml_trainer] epoch #147 | EpochTime 1766.62 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.9809 +Average/AverageReturn -54.3458 +Average/Iteration 147 +Average/MaxReturn -42.8057 +Average/MinReturn -101.226 +Average/NumEpisodes 120 +Average/StdReturn 7.77891 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89308 +GaussianMLPPolicy/KLAfter 0.00159137 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.37472e-05 +GaussianMLPPolicy/LossBefore 1.02917e-08 +GaussianMLPPolicy/dLoss 3.37575e-05 +Iteration 147 +MetaTest/Average/AverageDiscountedReturn -51.2905 +MetaTest/Average/AverageReturn -51.2905 +MetaTest/Average/Iteration 147 +MetaTest/Average/MaxReturn -44.6921 +MetaTest/Average/MinReturn -73.5933 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.18277 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2905 +MetaTest/__unnamed_task__/AverageReturn -51.2905 +MetaTest/__unnamed_task__/Iteration 147 +MetaTest/__unnamed_task__/MaxReturn -44.6921 +MetaTest/__unnamed_task__/MinReturn -73.5933 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.18277 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.104e+06 +__unnamed_task__/AverageDiscountedReturn -29.9809 +__unnamed_task__/AverageReturn -54.3458 +__unnamed_task__/Iteration 147 +__unnamed_task__/MaxReturn -42.8057 +__unnamed_task__/MinReturn -101.226 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.77891 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 13:42:20 | [maml_trainer] epoch #148 | Sampling for adapation and meta-testing... +2025-04-06 13:46:27 | [maml_trainer] epoch #148 | Finished meta-testing... +2025-04-06 13:46:27 | [maml_trainer] epoch #148 | Saving snapshot... +2025-04-06 13:46:50 | [maml_trainer] epoch #148 | Saved +2025-04-06 13:46:50 | [maml_trainer] epoch #148 | Time 248854.52 s +2025-04-06 13:46:50 | [maml_trainer] epoch #148 | EpochTime 1759.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.1289 +Average/AverageReturn -54.6637 +Average/Iteration 148 +Average/MaxReturn -42.2448 +Average/MinReturn -83.7794 +Average/NumEpisodes 120 +Average/StdReturn 7.29097 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8918 +GaussianMLPPolicy/KLAfter 0.00154597 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.18428e-06 +GaussianMLPPolicy/LossBefore -1.49012e-08 +GaussianMLPPolicy/dLoss -3.19918e-06 +Iteration 148 +MetaTest/Average/AverageDiscountedReturn -52.3356 +MetaTest/Average/AverageReturn -52.3356 +MetaTest/Average/Iteration 148 +MetaTest/Average/MaxReturn -43.4344 +MetaTest/Average/MinReturn -61.9125 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.54887 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3356 +MetaTest/__unnamed_task__/AverageReturn -52.3356 +MetaTest/__unnamed_task__/Iteration 148 +MetaTest/__unnamed_task__/MaxReturn -43.4344 +MetaTest/__unnamed_task__/MinReturn -61.9125 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.54887 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.152e+06 +__unnamed_task__/AverageDiscountedReturn -30.1289 +__unnamed_task__/AverageReturn -54.6637 +__unnamed_task__/Iteration 148 +__unnamed_task__/MaxReturn -42.2448 +__unnamed_task__/MinReturn -83.7794 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.29097 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 14:11:40 | [maml_trainer] epoch #149 | Sampling for adapation and meta-testing... +2025-04-06 14:15:49 | [maml_trainer] epoch #149 | Finished meta-testing... +2025-04-06 14:15:49 | [maml_trainer] epoch #149 | Saving snapshot... +2025-04-06 14:16:13 | [maml_trainer] epoch #149 | Saved +2025-04-06 14:16:13 | [maml_trainer] epoch #149 | Time 250617.21 s +2025-04-06 14:16:13 | [maml_trainer] epoch #149 | EpochTime 1762.69 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.0612 +Average/AverageReturn -54.8443 +Average/Iteration 149 +Average/MaxReturn -43.2767 +Average/MinReturn -87.328 +Average/NumEpisodes 120 +Average/StdReturn 7.80694 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89191 +GaussianMLPPolicy/KLAfter 0.00189454 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.5729e-05 +GaussianMLPPolicy/LossBefore -1.39078e-09 +GaussianMLPPolicy/dLoss -3.57304e-05 +Iteration 149 +MetaTest/Average/AverageDiscountedReturn -54.8855 +MetaTest/Average/AverageReturn -54.8855 +MetaTest/Average/Iteration 149 +MetaTest/Average/MaxReturn -45.8119 +MetaTest/Average/MinReturn -71.4792 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.95569 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.8855 +MetaTest/__unnamed_task__/AverageReturn -54.8855 +MetaTest/__unnamed_task__/Iteration 149 +MetaTest/__unnamed_task__/MaxReturn -45.8119 +MetaTest/__unnamed_task__/MinReturn -71.4792 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.95569 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.2e+06 +__unnamed_task__/AverageDiscountedReturn -30.0612 +__unnamed_task__/AverageReturn -54.8443 +__unnamed_task__/Iteration 149 +__unnamed_task__/MaxReturn -43.2767 +__unnamed_task__/MinReturn -87.328 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.80694 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 14:41:02 | [maml_trainer] epoch #150 | Sampling for adapation and meta-testing... +2025-04-06 14:45:15 | [maml_trainer] epoch #150 | Finished meta-testing... +2025-04-06 14:45:15 | [maml_trainer] epoch #150 | Saving snapshot... +2025-04-06 14:45:38 | [maml_trainer] epoch #150 | Saved +2025-04-06 14:45:38 | [maml_trainer] epoch #150 | Time 252382.15 s +2025-04-06 14:45:38 | [maml_trainer] epoch #150 | EpochTime 1764.93 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.9728 +Average/AverageReturn -54.4726 +Average/Iteration 150 +Average/MaxReturn -41.965 +Average/MinReturn -101.738 +Average/NumEpisodes 120 +Average/StdReturn 8.90933 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89326 +GaussianMLPPolicy/KLAfter 0.00193346 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.42881e-05 +GaussianMLPPolicy/LossBefore 2.38419e-09 +GaussianMLPPolicy/dLoss 8.42905e-05 +Iteration 150 +MetaTest/Average/AverageDiscountedReturn -52.4319 +MetaTest/Average/AverageReturn -52.4319 +MetaTest/Average/Iteration 150 +MetaTest/Average/MaxReturn -40.8627 +MetaTest/Average/MinReturn -120.099 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.1683 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.4319 +MetaTest/__unnamed_task__/AverageReturn -52.4319 +MetaTest/__unnamed_task__/Iteration 150 +MetaTest/__unnamed_task__/MaxReturn -40.8627 +MetaTest/__unnamed_task__/MinReturn -120.099 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.1683 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.248e+06 +__unnamed_task__/AverageDiscountedReturn -29.9728 +__unnamed_task__/AverageReturn -54.4726 +__unnamed_task__/Iteration 150 +__unnamed_task__/MaxReturn -41.965 +__unnamed_task__/MinReturn -101.738 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.90933 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 15:10:29 | [maml_trainer] epoch #151 | Sampling for adapation and meta-testing... +2025-04-06 15:14:36 | [maml_trainer] epoch #151 | Finished meta-testing... +2025-04-06 15:14:36 | [maml_trainer] epoch #151 | Saving snapshot... +2025-04-06 15:15:00 | [maml_trainer] epoch #151 | Saved +2025-04-06 15:15:00 | [maml_trainer] epoch #151 | Time 254144.09 s +2025-04-06 15:15:00 | [maml_trainer] epoch #151 | EpochTime 1761.94 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.7976 +Average/AverageReturn -53.9082 +Average/Iteration 151 +Average/MaxReturn 24.2686 +Average/MinReturn -93.6879 +Average/NumEpisodes 120 +Average/StdReturn 10.8602 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89356 +GaussianMLPPolicy/KLAfter 0.00108715 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.99141e-05 +GaussianMLPPolicy/LossBefore 1.86761e-09 +GaussianMLPPolicy/dLoss -1.99122e-05 +Iteration 151 +MetaTest/Average/AverageDiscountedReturn -53.4629 +MetaTest/Average/AverageReturn -53.4629 +MetaTest/Average/Iteration 151 +MetaTest/Average/MaxReturn -43.275 +MetaTest/Average/MinReturn -69.8149 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.53774 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4629 +MetaTest/__unnamed_task__/AverageReturn -53.4629 +MetaTest/__unnamed_task__/Iteration 151 +MetaTest/__unnamed_task__/MaxReturn -43.275 +MetaTest/__unnamed_task__/MinReturn -69.8149 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.53774 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.296e+06 +__unnamed_task__/AverageDiscountedReturn -29.7976 +__unnamed_task__/AverageReturn -53.9082 +__unnamed_task__/Iteration 151 +__unnamed_task__/MaxReturn 24.2686 +__unnamed_task__/MinReturn -93.6879 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.8602 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 15:40:00 | [maml_trainer] epoch #152 | Sampling for adapation and meta-testing... +2025-04-06 15:44:09 | [maml_trainer] epoch #152 | Finished meta-testing... +2025-04-06 15:44:09 | [maml_trainer] epoch #152 | Saving snapshot... +2025-04-06 15:44:32 | [maml_trainer] epoch #152 | Saved +2025-04-06 15:44:32 | [maml_trainer] epoch #152 | Time 255916.35 s +2025-04-06 15:44:32 | [maml_trainer] epoch #152 | EpochTime 1772.26 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.9475 +Average/AverageReturn -55.4914 +Average/Iteration 152 +Average/MaxReturn -19.0514 +Average/MinReturn -137.894 +Average/NumEpisodes 120 +Average/StdReturn 13.1645 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8957 +GaussianMLPPolicy/KLAfter 0.002448 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.90951e-05 +GaussianMLPPolicy/LossBefore 5.96046e-10 +GaussianMLPPolicy/dLoss -2.90945e-05 +Iteration 152 +MetaTest/Average/AverageDiscountedReturn -51.2971 +MetaTest/Average/AverageReturn -51.2971 +MetaTest/Average/Iteration 152 +MetaTest/Average/MaxReturn -43.5164 +MetaTest/Average/MinReturn -60.1193 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.27962 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2971 +MetaTest/__unnamed_task__/AverageReturn -51.2971 +MetaTest/__unnamed_task__/Iteration 152 +MetaTest/__unnamed_task__/MaxReturn -43.5164 +MetaTest/__unnamed_task__/MinReturn -60.1193 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.27962 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.344e+06 +__unnamed_task__/AverageDiscountedReturn -29.9475 +__unnamed_task__/AverageReturn -55.4914 +__unnamed_task__/Iteration 152 +__unnamed_task__/MaxReturn -19.0514 +__unnamed_task__/MinReturn -137.894 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.1645 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 16:09:35 | [maml_trainer] epoch #153 | Sampling for adapation and meta-testing... +2025-04-06 16:13:47 | [maml_trainer] epoch #153 | Finished meta-testing... +2025-04-06 16:13:47 | [maml_trainer] epoch #153 | Saving snapshot... +2025-04-06 16:14:10 | [maml_trainer] epoch #153 | Saved +2025-04-06 16:14:10 | [maml_trainer] epoch #153 | Time 257694.17 s +2025-04-06 16:14:10 | [maml_trainer] epoch #153 | EpochTime 1777.82 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.5656 +Average/AverageReturn -54.3205 +Average/Iteration 153 +Average/MaxReturn -41.1859 +Average/MinReturn -130.043 +Average/NumEpisodes 120 +Average/StdReturn 11.8205 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89726 +GaussianMLPPolicy/KLAfter 0.00199823 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.73594e-05 +GaussianMLPPolicy/LossBefore -3.73522e-09 +GaussianMLPPolicy/dLoss -7.73631e-05 +Iteration 153 +MetaTest/Average/AverageDiscountedReturn -59.6633 +MetaTest/Average/AverageReturn -59.6633 +MetaTest/Average/Iteration 153 +MetaTest/Average/MaxReturn -41.7943 +MetaTest/Average/MinReturn -150.556 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 23.7412 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -59.6633 +MetaTest/__unnamed_task__/AverageReturn -59.6633 +MetaTest/__unnamed_task__/Iteration 153 +MetaTest/__unnamed_task__/MaxReturn -41.7943 +MetaTest/__unnamed_task__/MinReturn -150.556 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 23.7412 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.392e+06 +__unnamed_task__/AverageDiscountedReturn -29.5656 +__unnamed_task__/AverageReturn -54.3205 +__unnamed_task__/Iteration 153 +__unnamed_task__/MaxReturn -41.1859 +__unnamed_task__/MinReturn -130.043 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.8205 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 16:39:22 | [maml_trainer] epoch #154 | Sampling for adapation and meta-testing... +2025-04-06 16:43:33 | [maml_trainer] epoch #154 | Finished meta-testing... +2025-04-06 16:43:33 | [maml_trainer] epoch #154 | Saving snapshot... +2025-04-06 16:43:56 | [maml_trainer] epoch #154 | Saved +2025-04-06 16:43:56 | [maml_trainer] epoch #154 | Time 259480.03 s +2025-04-06 16:43:56 | [maml_trainer] epoch #154 | EpochTime 1785.85 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.9334 +Average/AverageReturn -55.2007 +Average/Iteration 154 +Average/MaxReturn -41.8064 +Average/MinReturn -144.594 +Average/NumEpisodes 120 +Average/StdReturn 13.066 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89683 +GaussianMLPPolicy/KLAfter 0.00161973 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.2803e-05 +GaussianMLPPolicy/LossBefore -5.08626e-09 +GaussianMLPPolicy/dLoss 2.27979e-05 +Iteration 154 +MetaTest/Average/AverageDiscountedReturn -57.7769 +MetaTest/Average/AverageReturn -57.7769 +MetaTest/Average/Iteration 154 +MetaTest/Average/MaxReturn -41.6841 +MetaTest/Average/MinReturn -112.182 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.5852 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.7769 +MetaTest/__unnamed_task__/AverageReturn -57.7769 +MetaTest/__unnamed_task__/Iteration 154 +MetaTest/__unnamed_task__/MaxReturn -41.6841 +MetaTest/__unnamed_task__/MinReturn -112.182 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.5852 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.44e+06 +__unnamed_task__/AverageDiscountedReturn -29.9334 +__unnamed_task__/AverageReturn -55.2007 +__unnamed_task__/Iteration 154 +__unnamed_task__/MaxReturn -41.8064 +__unnamed_task__/MinReturn -144.594 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.066 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 17:09:15 | [maml_trainer] epoch #155 | Sampling for adapation and meta-testing... +2025-04-06 17:13:29 | [maml_trainer] epoch #155 | Finished meta-testing... +2025-04-06 17:13:29 | [maml_trainer] epoch #155 | Saving snapshot... +2025-04-06 17:13:53 | [maml_trainer] epoch #155 | Saved +2025-04-06 17:13:53 | [maml_trainer] epoch #155 | Time 261277.29 s +2025-04-06 17:13:53 | [maml_trainer] epoch #155 | EpochTime 1797.25 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.68 +Average/AverageReturn -54.4395 +Average/Iteration 155 +Average/MaxReturn -31.6299 +Average/MinReturn -135.771 +Average/NumEpisodes 120 +Average/StdReturn 11.9795 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89672 +GaussianMLPPolicy/KLAfter 0.00135864 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.9565e-05 +GaussianMLPPolicy/LossBefore -7.43071e-09 +GaussianMLPPolicy/dLoss 4.95576e-05 +Iteration 155 +MetaTest/Average/AverageDiscountedReturn -54.2959 +MetaTest/Average/AverageReturn -54.2959 +MetaTest/Average/Iteration 155 +MetaTest/Average/MaxReturn -42.9612 +MetaTest/Average/MinReturn -82.7055 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.89392 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2959 +MetaTest/__unnamed_task__/AverageReturn -54.2959 +MetaTest/__unnamed_task__/Iteration 155 +MetaTest/__unnamed_task__/MaxReturn -42.9612 +MetaTest/__unnamed_task__/MinReturn -82.7055 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.89392 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.488e+06 +__unnamed_task__/AverageDiscountedReturn -29.68 +__unnamed_task__/AverageReturn -54.4395 +__unnamed_task__/Iteration 155 +__unnamed_task__/MaxReturn -31.6299 +__unnamed_task__/MinReturn -135.771 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.9795 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 17:38:56 | [maml_trainer] epoch #156 | Sampling for adapation and meta-testing... +2025-04-06 17:43:05 | [maml_trainer] epoch #156 | Finished meta-testing... +2025-04-06 17:43:05 | [maml_trainer] epoch #156 | Saving snapshot... +2025-04-06 17:43:29 | [maml_trainer] epoch #156 | Saved +2025-04-06 17:43:29 | [maml_trainer] epoch #156 | Time 263053.05 s +2025-04-06 17:43:29 | [maml_trainer] epoch #156 | EpochTime 1775.76 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.009 +Average/AverageReturn -52.2083 +Average/Iteration 156 +Average/MaxReturn 1.7885 +Average/MinReturn -139.842 +Average/NumEpisodes 120 +Average/StdReturn 12.5974 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89661 +GaussianMLPPolicy/KLAfter 0.0020529 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.92978e-05 +GaussianMLPPolicy/LossBefore 6.39757e-09 +GaussianMLPPolicy/dLoss 2.93042e-05 +Iteration 156 +MetaTest/Average/AverageDiscountedReturn -51.6631 +MetaTest/Average/AverageReturn -51.6631 +MetaTest/Average/Iteration 156 +MetaTest/Average/MaxReturn -38.4777 +MetaTest/Average/MinReturn -67.0042 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.38126 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6631 +MetaTest/__unnamed_task__/AverageReturn -51.6631 +MetaTest/__unnamed_task__/Iteration 156 +MetaTest/__unnamed_task__/MaxReturn -38.4777 +MetaTest/__unnamed_task__/MinReturn -67.0042 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.38126 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.536e+06 +__unnamed_task__/AverageDiscountedReturn -29.009 +__unnamed_task__/AverageReturn -52.2083 +__unnamed_task__/Iteration 156 +__unnamed_task__/MaxReturn 1.7885 +__unnamed_task__/MinReturn -139.842 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.5974 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 18:08:42 | [maml_trainer] epoch #157 | Sampling for adapation and meta-testing... +2025-04-06 18:12:54 | [maml_trainer] epoch #157 | Finished meta-testing... +2025-04-06 18:12:54 | [maml_trainer] epoch #157 | Saving snapshot... +2025-04-06 18:13:17 | [maml_trainer] epoch #157 | Saved +2025-04-06 18:13:17 | [maml_trainer] epoch #157 | Time 264841.07 s +2025-04-06 18:13:17 | [maml_trainer] epoch #157 | EpochTime 1788.01 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.2642 +Average/AverageReturn -53.1274 +Average/Iteration 157 +Average/MaxReturn -40.9791 +Average/MinReturn -100.876 +Average/NumEpisodes 120 +Average/StdReturn 8.88837 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89662 +GaussianMLPPolicy/KLAfter 0.00247779 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.34019e-05 +GaussianMLPPolicy/LossBefore 4.29153e-09 +GaussianMLPPolicy/dLoss 1.34062e-05 +Iteration 157 +MetaTest/Average/AverageDiscountedReturn -53.4563 +MetaTest/Average/AverageReturn -53.4563 +MetaTest/Average/Iteration 157 +MetaTest/Average/MaxReturn -43.5865 +MetaTest/Average/MinReturn -76.2738 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.2838 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4563 +MetaTest/__unnamed_task__/AverageReturn -53.4563 +MetaTest/__unnamed_task__/Iteration 157 +MetaTest/__unnamed_task__/MaxReturn -43.5865 +MetaTest/__unnamed_task__/MinReturn -76.2738 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.2838 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.584e+06 +__unnamed_task__/AverageDiscountedReturn -29.2642 +__unnamed_task__/AverageReturn -53.1274 +__unnamed_task__/Iteration 157 +__unnamed_task__/MaxReturn -40.9791 +__unnamed_task__/MinReturn -100.876 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.88837 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 18:38:32 | [maml_trainer] epoch #158 | Sampling for adapation and meta-testing... +2025-04-06 18:42:43 | [maml_trainer] epoch #158 | Finished meta-testing... +2025-04-06 18:42:43 | [maml_trainer] epoch #158 | Saving snapshot... +2025-04-06 18:43:06 | [maml_trainer] epoch #158 | Saved +2025-04-06 18:43:06 | [maml_trainer] epoch #158 | Time 266630.29 s +2025-04-06 18:43:06 | [maml_trainer] epoch #158 | EpochTime 1789.22 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.1147 +Average/AverageReturn -52.6239 +Average/Iteration 158 +Average/MaxReturn 509.617 +Average/MinReturn -177.78 +Average/NumEpisodes 120 +Average/StdReturn 57.332 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89545 +GaussianMLPPolicy/KLAfter 0.00347703 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.42438e-06 +GaussianMLPPolicy/LossBefore 7.30157e-10 +GaussianMLPPolicy/dLoss -6.42365e-06 +Iteration 158 +MetaTest/Average/AverageDiscountedReturn -51.8264 +MetaTest/Average/AverageReturn -51.8264 +MetaTest/Average/Iteration 158 +MetaTest/Average/MaxReturn -42.8014 +MetaTest/Average/MinReturn -70.9208 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.50375 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8264 +MetaTest/__unnamed_task__/AverageReturn -51.8264 +MetaTest/__unnamed_task__/Iteration 158 +MetaTest/__unnamed_task__/MaxReturn -42.8014 +MetaTest/__unnamed_task__/MinReturn -70.9208 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.50375 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.632e+06 +__unnamed_task__/AverageDiscountedReturn -29.1147 +__unnamed_task__/AverageReturn -52.6239 +__unnamed_task__/Iteration 158 +__unnamed_task__/MaxReturn 509.617 +__unnamed_task__/MinReturn -177.78 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 57.332 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 19:08:15 | [maml_trainer] epoch #159 | Sampling for adapation and meta-testing... +2025-04-06 19:12:27 | [maml_trainer] epoch #159 | Finished meta-testing... +2025-04-06 19:12:27 | [maml_trainer] epoch #159 | Saving snapshot... +2025-04-06 19:12:50 | [maml_trainer] epoch #159 | Saved +2025-04-06 19:12:50 | [maml_trainer] epoch #159 | Time 268414.02 s +2025-04-06 19:12:50 | [maml_trainer] epoch #159 | EpochTime 1783.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.4445 +Average/AverageReturn -53.944 +Average/Iteration 159 +Average/MaxReturn -39.3463 +Average/MinReturn -104.588 +Average/NumEpisodes 120 +Average/StdReturn 9.28087 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89297 +GaussianMLPPolicy/KLAfter 0.00344776 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.2365e-05 +GaussianMLPPolicy/LossBefore -2.78155e-10 +GaussianMLPPolicy/dLoss 5.23647e-05 +Iteration 159 +MetaTest/Average/AverageDiscountedReturn -55.6394 +MetaTest/Average/AverageReturn -55.6394 +MetaTest/Average/Iteration 159 +MetaTest/Average/MaxReturn -43.485 +MetaTest/Average/MinReturn -127.339 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.335 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6394 +MetaTest/__unnamed_task__/AverageReturn -55.6394 +MetaTest/__unnamed_task__/Iteration 159 +MetaTest/__unnamed_task__/MaxReturn -43.485 +MetaTest/__unnamed_task__/MinReturn -127.339 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.335 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.68e+06 +__unnamed_task__/AverageDiscountedReturn -29.4445 +__unnamed_task__/AverageReturn -53.944 +__unnamed_task__/Iteration 159 +__unnamed_task__/MaxReturn -39.3463 +__unnamed_task__/MinReturn -104.588 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.28087 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 19:38:05 | [maml_trainer] epoch #160 | Sampling for adapation and meta-testing... +2025-04-06 19:42:12 | [maml_trainer] epoch #160 | Finished meta-testing... +2025-04-06 19:42:12 | [maml_trainer] epoch #160 | Saving snapshot... +2025-04-06 19:42:35 | [maml_trainer] epoch #160 | Saved +2025-04-06 19:42:35 | [maml_trainer] epoch #160 | Time 270199.62 s +2025-04-06 19:42:35 | [maml_trainer] epoch #160 | EpochTime 1785.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.8954 +Average/AverageReturn -53.1207 +Average/Iteration 160 +Average/MaxReturn -41.6086 +Average/MinReturn -109.475 +Average/NumEpisodes 120 +Average/StdReturn 9.91445 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89155 +GaussianMLPPolicy/KLAfter 0.00265257 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.81773e-06 +GaussianMLPPolicy/LossBefore 1.19209e-10 +GaussianMLPPolicy/dLoss -5.81761e-06 +Iteration 160 +MetaTest/Average/AverageDiscountedReturn -54.7186 +MetaTest/Average/AverageReturn -54.7186 +MetaTest/Average/Iteration 160 +MetaTest/Average/MaxReturn -44.638 +MetaTest/Average/MinReturn -106.729 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.8087 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.7186 +MetaTest/__unnamed_task__/AverageReturn -54.7186 +MetaTest/__unnamed_task__/Iteration 160 +MetaTest/__unnamed_task__/MaxReturn -44.638 +MetaTest/__unnamed_task__/MinReturn -106.729 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.8087 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.728e+06 +__unnamed_task__/AverageDiscountedReturn -28.8954 +__unnamed_task__/AverageReturn -53.1207 +__unnamed_task__/Iteration 160 +__unnamed_task__/MaxReturn -41.6086 +__unnamed_task__/MinReturn -109.475 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.91445 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 20:07:55 | [maml_trainer] epoch #161 | Sampling for adapation and meta-testing... +2025-04-06 20:12:07 | [maml_trainer] epoch #161 | Finished meta-testing... +2025-04-06 20:12:07 | [maml_trainer] epoch #161 | Saving snapshot... +2025-04-06 20:12:30 | [maml_trainer] epoch #161 | Saved +2025-04-06 20:12:30 | [maml_trainer] epoch #161 | Time 271994.67 s +2025-04-06 20:12:30 | [maml_trainer] epoch #161 | EpochTime 1795.04 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3692 +Average/AverageReturn -50.0486 +Average/Iteration 161 +Average/MaxReturn 78.6825 +Average/MinReturn -86.4224 +Average/NumEpisodes 120 +Average/StdReturn 13.8374 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89077 +GaussianMLPPolicy/KLAfter 0.00143265 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.50599e-05 +GaussianMLPPolicy/LossBefore -2.1855e-09 +GaussianMLPPolicy/dLoss 2.50578e-05 +Iteration 161 +MetaTest/Average/AverageDiscountedReturn -49.3308 +MetaTest/Average/AverageReturn -49.3308 +MetaTest/Average/Iteration 161 +MetaTest/Average/MaxReturn -43.1038 +MetaTest/Average/MinReturn -58.5326 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.6073 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3308 +MetaTest/__unnamed_task__/AverageReturn -49.3308 +MetaTest/__unnamed_task__/Iteration 161 +MetaTest/__unnamed_task__/MaxReturn -43.1038 +MetaTest/__unnamed_task__/MinReturn -58.5326 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.6073 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.776e+06 +__unnamed_task__/AverageDiscountedReturn -28.3692 +__unnamed_task__/AverageReturn -50.0486 +__unnamed_task__/Iteration 161 +__unnamed_task__/MaxReturn 78.6825 +__unnamed_task__/MinReturn -86.4224 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.8374 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 20:37:41 | [maml_trainer] epoch #162 | Sampling for adapation and meta-testing... +2025-04-06 20:41:55 | [maml_trainer] epoch #162 | Finished meta-testing... +2025-04-06 20:41:55 | [maml_trainer] epoch #162 | Saving snapshot... +2025-04-06 20:42:18 | [maml_trainer] epoch #162 | Saved +2025-04-06 20:42:18 | [maml_trainer] epoch #162 | Time 273782.69 s +2025-04-06 20:42:18 | [maml_trainer] epoch #162 | EpochTime 1788.02 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.7132 +Average/AverageReturn -52.0309 +Average/Iteration 162 +Average/MaxReturn -41.826 +Average/MinReturn -124.176 +Average/NumEpisodes 120 +Average/StdReturn 9.13809 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.89026 +GaussianMLPPolicy/KLAfter 0.000828314 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.1327e-05 +GaussianMLPPolicy/LossBefore -4.01338e-09 +GaussianMLPPolicy/dLoss 1.1323e-05 +Iteration 162 +MetaTest/Average/AverageDiscountedReturn -52.2269 +MetaTest/Average/AverageReturn -52.2269 +MetaTest/Average/Iteration 162 +MetaTest/Average/MaxReturn -43.4828 +MetaTest/Average/MinReturn -90.317 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.5575 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2269 +MetaTest/__unnamed_task__/AverageReturn -52.2269 +MetaTest/__unnamed_task__/Iteration 162 +MetaTest/__unnamed_task__/MaxReturn -43.4828 +MetaTest/__unnamed_task__/MinReturn -90.317 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.5575 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.824e+06 +__unnamed_task__/AverageDiscountedReturn -28.7132 +__unnamed_task__/AverageReturn -52.0309 +__unnamed_task__/Iteration 162 +__unnamed_task__/MaxReturn -41.826 +__unnamed_task__/MinReturn -124.176 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.13809 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-06 21:07:33 | [maml_trainer] epoch #163 | Sampling for adapation and meta-testing... +2025-04-06 21:11:45 | [maml_trainer] epoch #163 | Finished meta-testing... +2025-04-06 21:11:45 | [maml_trainer] epoch #163 | Saving snapshot... +2025-04-06 21:12:09 | [maml_trainer] epoch #163 | Saved +2025-04-06 21:12:09 | [maml_trainer] epoch #163 | Time 275573.09 s +2025-04-06 21:12:09 | [maml_trainer] epoch #163 | EpochTime 1790.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4339 +Average/AverageReturn -51.2563 +Average/Iteration 163 +Average/MaxReturn -42.7068 +Average/MinReturn -90.3291 +Average/NumEpisodes 120 +Average/StdReturn 6.43503 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88865 +GaussianMLPPolicy/KLAfter 0.00101748 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.8251e-06 +GaussianMLPPolicy/LossBefore 4.17232e-09 +GaussianMLPPolicy/dLoss -8.82093e-06 +Iteration 163 +MetaTest/Average/AverageDiscountedReturn -52.1758 +MetaTest/Average/AverageReturn -52.1758 +MetaTest/Average/Iteration 163 +MetaTest/Average/MaxReturn -43.2032 +MetaTest/Average/MinReturn -81.7468 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.47279 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1758 +MetaTest/__unnamed_task__/AverageReturn -52.1758 +MetaTest/__unnamed_task__/Iteration 163 +MetaTest/__unnamed_task__/MaxReturn -43.2032 +MetaTest/__unnamed_task__/MinReturn -81.7468 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.47279 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.872e+06 +__unnamed_task__/AverageDiscountedReturn -28.4339 +__unnamed_task__/AverageReturn -51.2563 +__unnamed_task__/Iteration 163 +__unnamed_task__/MaxReturn -42.7068 +__unnamed_task__/MinReturn -90.3291 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.43503 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 21:37:28 | [maml_trainer] epoch #164 | Sampling for adapation and meta-testing... +2025-04-06 21:41:40 | [maml_trainer] epoch #164 | Finished meta-testing... +2025-04-06 21:41:40 | [maml_trainer] epoch #164 | Saving snapshot... +2025-04-06 21:42:03 | [maml_trainer] epoch #164 | Saved +2025-04-06 21:42:03 | [maml_trainer] epoch #164 | Time 277367.76 s +2025-04-06 21:42:03 | [maml_trainer] epoch #164 | EpochTime 1794.66 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6812 +Average/AverageReturn -51.8748 +Average/Iteration 164 +Average/MaxReturn -39.5472 +Average/MinReturn -93.8018 +Average/NumEpisodes 120 +Average/StdReturn 7.77734 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88776 +GaussianMLPPolicy/KLAfter 0.00104438 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.77709e-05 +GaussianMLPPolicy/LossBefore -3.41733e-09 +GaussianMLPPolicy/dLoss 2.77675e-05 +Iteration 164 +MetaTest/Average/AverageDiscountedReturn -49.4038 +MetaTest/Average/AverageReturn -49.4038 +MetaTest/Average/Iteration 164 +MetaTest/Average/MaxReturn -44.7006 +MetaTest/Average/MinReturn -59.8569 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.28248 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.4038 +MetaTest/__unnamed_task__/AverageReturn -49.4038 +MetaTest/__unnamed_task__/Iteration 164 +MetaTest/__unnamed_task__/MaxReturn -44.7006 +MetaTest/__unnamed_task__/MinReturn -59.8569 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.28248 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.92e+06 +__unnamed_task__/AverageDiscountedReturn -28.6812 +__unnamed_task__/AverageReturn -51.8748 +__unnamed_task__/Iteration 164 +__unnamed_task__/MaxReturn -39.5472 +__unnamed_task__/MinReturn -93.8018 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.77734 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 22:07:36 | [maml_trainer] epoch #165 | Sampling for adapation and meta-testing... +2025-04-06 22:11:49 | [maml_trainer] epoch #165 | Finished meta-testing... +2025-04-06 22:11:49 | [maml_trainer] epoch #165 | Saving snapshot... +2025-04-06 22:12:12 | [maml_trainer] epoch #165 | Saved +2025-04-06 22:12:12 | [maml_trainer] epoch #165 | Time 279176.23 s +2025-04-06 22:12:12 | [maml_trainer] epoch #165 | EpochTime 1808.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4096 +Average/AverageReturn -50.8491 +Average/Iteration 165 +Average/MaxReturn -42.8447 +Average/MinReturn -70.5569 +Average/NumEpisodes 120 +Average/StdReturn 5.25015 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88774 +GaussianMLPPolicy/KLAfter 0.00135766 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.26017e-05 +GaussianMLPPolicy/LossBefore -2.22524e-09 +GaussianMLPPolicy/dLoss 2.25995e-05 +Iteration 165 +MetaTest/Average/AverageDiscountedReturn -49.5613 +MetaTest/Average/AverageReturn -49.5613 +MetaTest/Average/Iteration 165 +MetaTest/Average/MaxReturn -41.5629 +MetaTest/Average/MinReturn -56.2934 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.44545 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5613 +MetaTest/__unnamed_task__/AverageReturn -49.5613 +MetaTest/__unnamed_task__/Iteration 165 +MetaTest/__unnamed_task__/MaxReturn -41.5629 +MetaTest/__unnamed_task__/MinReturn -56.2934 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.44545 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 7.968e+06 +__unnamed_task__/AverageDiscountedReturn -28.4096 +__unnamed_task__/AverageReturn -50.8491 +__unnamed_task__/Iteration 165 +__unnamed_task__/MaxReturn -42.8447 +__unnamed_task__/MinReturn -70.5569 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.25015 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 22:37:24 | [maml_trainer] epoch #166 | Sampling for adapation and meta-testing... +2025-04-06 22:41:37 | [maml_trainer] epoch #166 | Finished meta-testing... +2025-04-06 22:41:37 | [maml_trainer] epoch #166 | Saving snapshot... +2025-04-06 22:42:00 | [maml_trainer] epoch #166 | Saved +2025-04-06 22:42:00 | [maml_trainer] epoch #166 | Time 280964.34 s +2025-04-06 22:42:00 | [maml_trainer] epoch #166 | EpochTime 1788.10 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3978 +Average/AverageReturn -51.2251 +Average/Iteration 166 +Average/MaxReturn -41.9919 +Average/MinReturn -81.4965 +Average/NumEpisodes 120 +Average/StdReturn 5.98791 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88722 +GaussianMLPPolicy/KLAfter 0.00107252 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.52723e-05 +GaussianMLPPolicy/LossBefore -1.34707e-08 +GaussianMLPPolicy/dLoss -4.52858e-05 +Iteration 166 +MetaTest/Average/AverageDiscountedReturn -50.5331 +MetaTest/Average/AverageReturn -50.5331 +MetaTest/Average/Iteration 166 +MetaTest/Average/MaxReturn -43.5633 +MetaTest/Average/MinReturn -55.647 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.03696 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5331 +MetaTest/__unnamed_task__/AverageReturn -50.5331 +MetaTest/__unnamed_task__/Iteration 166 +MetaTest/__unnamed_task__/MaxReturn -43.5633 +MetaTest/__unnamed_task__/MinReturn -55.647 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.03696 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.016e+06 +__unnamed_task__/AverageDiscountedReturn -28.3978 +__unnamed_task__/AverageReturn -51.2251 +__unnamed_task__/Iteration 166 +__unnamed_task__/MaxReturn -41.9919 +__unnamed_task__/MinReturn -81.4965 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.98791 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 23:07:10 | [maml_trainer] epoch #167 | Sampling for adapation and meta-testing... +2025-04-06 23:11:20 | [maml_trainer] epoch #167 | Finished meta-testing... +2025-04-06 23:11:20 | [maml_trainer] epoch #167 | Saving snapshot... +2025-04-06 23:11:44 | [maml_trainer] epoch #167 | Saved +2025-04-06 23:11:44 | [maml_trainer] epoch #167 | Time 282748.02 s +2025-04-06 23:11:44 | [maml_trainer] epoch #167 | EpochTime 1783.67 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8953 +Average/AverageReturn -49.6875 +Average/Iteration 167 +Average/MaxReturn 15.8952 +Average/MinReturn -68.2804 +Average/NumEpisodes 120 +Average/StdReturn 8.24116 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88638 +GaussianMLPPolicy/KLAfter 0.00275432 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000158284 +GaussianMLPPolicy/LossBefore -1.82788e-08 +GaussianMLPPolicy/dLoss 0.000158266 +Iteration 167 +MetaTest/Average/AverageDiscountedReturn -49.217 +MetaTest/Average/AverageReturn -49.217 +MetaTest/Average/Iteration 167 +MetaTest/Average/MaxReturn -39.0323 +MetaTest/Average/MinReturn -61.0983 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.6955 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.217 +MetaTest/__unnamed_task__/AverageReturn -49.217 +MetaTest/__unnamed_task__/Iteration 167 +MetaTest/__unnamed_task__/MaxReturn -39.0323 +MetaTest/__unnamed_task__/MinReturn -61.0983 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.6955 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.064e+06 +__unnamed_task__/AverageDiscountedReturn -27.8953 +__unnamed_task__/AverageReturn -49.6875 +__unnamed_task__/Iteration 167 +__unnamed_task__/MaxReturn 15.8952 +__unnamed_task__/MinReturn -68.2804 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.24116 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-06 23:36:56 | [maml_trainer] epoch #168 | Sampling for adapation and meta-testing... +2025-04-06 23:41:09 | [maml_trainer] epoch #168 | Finished meta-testing... +2025-04-06 23:41:09 | [maml_trainer] epoch #168 | Saving snapshot... +2025-04-06 23:41:32 | [maml_trainer] epoch #168 | Saved +2025-04-06 23:41:32 | [maml_trainer] epoch #168 | Time 284536.56 s +2025-04-06 23:41:32 | [maml_trainer] epoch #168 | EpochTime 1788.54 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2717 +Average/AverageReturn -45.0028 +Average/Iteration 168 +Average/MaxReturn 355.204 +Average/MinReturn -108.926 +Average/NumEpisodes 120 +Average/StdReturn 40.5248 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88489 +GaussianMLPPolicy/KLAfter 0.00313708 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.51536e-05 +GaussianMLPPolicy/LossBefore -1.02818e-09 +GaussianMLPPolicy/dLoss -1.51546e-05 +Iteration 168 +MetaTest/Average/AverageDiscountedReturn -50.1065 +MetaTest/Average/AverageReturn -50.1065 +MetaTest/Average/Iteration 168 +MetaTest/Average/MaxReturn -40.4539 +MetaTest/Average/MinReturn -61.9234 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.28822 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1065 +MetaTest/__unnamed_task__/AverageReturn -50.1065 +MetaTest/__unnamed_task__/Iteration 168 +MetaTest/__unnamed_task__/MaxReturn -40.4539 +MetaTest/__unnamed_task__/MinReturn -61.9234 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.28822 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.112e+06 +__unnamed_task__/AverageDiscountedReturn -27.2717 +__unnamed_task__/AverageReturn -45.0028 +__unnamed_task__/Iteration 168 +__unnamed_task__/MaxReturn 355.204 +__unnamed_task__/MinReturn -108.926 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 40.5248 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 00:06:49 | [maml_trainer] epoch #169 | Sampling for adapation and meta-testing... +2025-04-07 00:10:55 | [maml_trainer] epoch #169 | Finished meta-testing... +2025-04-07 00:10:55 | [maml_trainer] epoch #169 | Saving snapshot... +2025-04-07 00:11:16 | [maml_trainer] epoch #169 | Saved +2025-04-07 00:11:16 | [maml_trainer] epoch #169 | Time 286320.63 s +2025-04-07 00:11:16 | [maml_trainer] epoch #169 | EpochTime 1784.06 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.1185 +Average/AverageReturn -51.4442 +Average/Iteration 169 +Average/MaxReturn -11.9761 +Average/MinReturn -107.447 +Average/NumEpisodes 120 +Average/StdReturn 11.9823 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88359 +GaussianMLPPolicy/KLAfter 0.00387623 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.03897e-05 +GaussianMLPPolicy/LossBefore -3.77496e-09 +GaussianMLPPolicy/dLoss 7.03859e-05 +Iteration 169 +MetaTest/Average/AverageDiscountedReturn -49.3207 +MetaTest/Average/AverageReturn -49.3207 +MetaTest/Average/Iteration 169 +MetaTest/Average/MaxReturn -43.2061 +MetaTest/Average/MinReturn -57.9725 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.01087 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3207 +MetaTest/__unnamed_task__/AverageReturn -49.3207 +MetaTest/__unnamed_task__/Iteration 169 +MetaTest/__unnamed_task__/MaxReturn -43.2061 +MetaTest/__unnamed_task__/MinReturn -57.9725 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.01087 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.16e+06 +__unnamed_task__/AverageDiscountedReturn -28.1185 +__unnamed_task__/AverageReturn -51.4442 +__unnamed_task__/Iteration 169 +__unnamed_task__/MaxReturn -11.9761 +__unnamed_task__/MinReturn -107.447 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.9823 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 00:34:50 | [maml_trainer] epoch #170 | Sampling for adapation and meta-testing... +2025-04-07 00:38:50 | [maml_trainer] epoch #170 | Finished meta-testing... +2025-04-07 00:38:50 | [maml_trainer] epoch #170 | Saving snapshot... +2025-04-07 00:39:12 | [maml_trainer] epoch #170 | Saved +2025-04-07 00:39:12 | [maml_trainer] epoch #170 | Time 287996.53 s +2025-04-07 00:39:12 | [maml_trainer] epoch #170 | EpochTime 1675.90 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.2569 +Average/AverageReturn -52.5721 +Average/Iteration 170 +Average/MaxReturn -25.7313 +Average/MinReturn -151.247 +Average/NumEpisodes 120 +Average/StdReturn 15.5111 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88284 +GaussianMLPPolicy/KLAfter 0.00231294 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.85812e-05 +GaussianMLPPolicy/LossBefore 3.47694e-09 +GaussianMLPPolicy/dLoss -3.85777e-05 +Iteration 170 +MetaTest/Average/AverageDiscountedReturn -50.5576 +MetaTest/Average/AverageReturn -50.5576 +MetaTest/Average/Iteration 170 +MetaTest/Average/MaxReturn -40.7147 +MetaTest/Average/MinReturn -79.2781 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.08988 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5576 +MetaTest/__unnamed_task__/AverageReturn -50.5576 +MetaTest/__unnamed_task__/Iteration 170 +MetaTest/__unnamed_task__/MaxReturn -40.7147 +MetaTest/__unnamed_task__/MinReturn -79.2781 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.08988 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.208e+06 +__unnamed_task__/AverageDiscountedReturn -28.2569 +__unnamed_task__/AverageReturn -52.5721 +__unnamed_task__/Iteration 170 +__unnamed_task__/MaxReturn -25.7313 +__unnamed_task__/MinReturn -151.247 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.5111 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 01:02:58 | [maml_trainer] epoch #171 | Sampling for adapation and meta-testing... +2025-04-07 01:06:58 | [maml_trainer] epoch #171 | Finished meta-testing... +2025-04-07 01:06:59 | [maml_trainer] epoch #171 | Saving snapshot... +2025-04-07 01:07:20 | [maml_trainer] epoch #171 | Saved +2025-04-07 01:07:20 | [maml_trainer] epoch #171 | Time 289684.58 s +2025-04-07 01:07:20 | [maml_trainer] epoch #171 | EpochTime 1688.05 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.1944 +Average/AverageReturn -50.9449 +Average/Iteration 171 +Average/MaxReturn 273.623 +Average/MinReturn -174.181 +Average/NumEpisodes 120 +Average/StdReturn 39.7076 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88283 +GaussianMLPPolicy/KLAfter 0.00134532 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.9859e-05 +GaussianMLPPolicy/LossBefore -8.19564e-10 +GaussianMLPPolicy/dLoss 1.98582e-05 +Iteration 171 +MetaTest/Average/AverageDiscountedReturn -51.6719 +MetaTest/Average/AverageReturn -51.6719 +MetaTest/Average/Iteration 171 +MetaTest/Average/MaxReturn -42.5015 +MetaTest/Average/MinReturn -65.662 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.61795 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6719 +MetaTest/__unnamed_task__/AverageReturn -51.6719 +MetaTest/__unnamed_task__/Iteration 171 +MetaTest/__unnamed_task__/MaxReturn -42.5015 +MetaTest/__unnamed_task__/MinReturn -65.662 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.61795 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.256e+06 +__unnamed_task__/AverageDiscountedReturn -28.1944 +__unnamed_task__/AverageReturn -50.9449 +__unnamed_task__/Iteration 171 +__unnamed_task__/MaxReturn 273.623 +__unnamed_task__/MinReturn -174.181 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 39.7076 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 01:31:01 | [maml_trainer] epoch #172 | Sampling for adapation and meta-testing... +2025-04-07 01:35:02 | [maml_trainer] epoch #172 | Finished meta-testing... +2025-04-07 01:35:02 | [maml_trainer] epoch #172 | Saving snapshot... +2025-04-07 01:35:24 | [maml_trainer] epoch #172 | Saved +2025-04-07 01:35:24 | [maml_trainer] epoch #172 | Time 291368.60 s +2025-04-07 01:35:24 | [maml_trainer] epoch #172 | EpochTime 1684.02 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.9814 +Average/AverageReturn -53.4037 +Average/Iteration 172 +Average/MaxReturn -39.1743 +Average/MinReturn -176.847 +Average/NumEpisodes 120 +Average/StdReturn 20.3584 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88275 +GaussianMLPPolicy/KLAfter 0.0017286 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.27351e-06 +GaussianMLPPolicy/LossBefore 2.5034e-09 +GaussianMLPPolicy/dLoss -3.271e-06 +Iteration 172 +MetaTest/Average/AverageDiscountedReturn -54.1463 +MetaTest/Average/AverageReturn -54.1463 +MetaTest/Average/Iteration 172 +MetaTest/Average/MaxReturn -43.6847 +MetaTest/Average/MinReturn -87.4727 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.9063 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1463 +MetaTest/__unnamed_task__/AverageReturn -54.1463 +MetaTest/__unnamed_task__/Iteration 172 +MetaTest/__unnamed_task__/MaxReturn -43.6847 +MetaTest/__unnamed_task__/MinReturn -87.4727 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.9063 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.304e+06 +__unnamed_task__/AverageDiscountedReturn -27.9814 +__unnamed_task__/AverageReturn -53.4037 +__unnamed_task__/Iteration 172 +__unnamed_task__/MaxReturn -39.1743 +__unnamed_task__/MinReturn -176.847 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.3584 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 01:59:19 | [maml_trainer] epoch #173 | Sampling for adapation and meta-testing... +2025-04-07 02:03:14 | [maml_trainer] epoch #173 | Finished meta-testing... +2025-04-07 02:03:14 | [maml_trainer] epoch #173 | Saving snapshot... +2025-04-07 02:03:35 | [maml_trainer] epoch #173 | Saved +2025-04-07 02:03:35 | [maml_trainer] epoch #173 | Time 293059.23 s +2025-04-07 02:03:35 | [maml_trainer] epoch #173 | EpochTime 1690.63 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.1233 +Average/AverageReturn -56.9754 +Average/Iteration 173 +Average/MaxReturn -21.7759 +Average/MinReturn -178.944 +Average/NumEpisodes 120 +Average/StdReturn 23.9541 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88277 +GaussianMLPPolicy/KLAfter 0.00177074 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.81032e-05 +GaussianMLPPolicy/LossBefore 9.93411e-10 +GaussianMLPPolicy/dLoss 3.81042e-05 +Iteration 173 +MetaTest/Average/AverageDiscountedReturn -54.0498 +MetaTest/Average/AverageReturn -54.0498 +MetaTest/Average/Iteration 173 +MetaTest/Average/MaxReturn -16.2336 +MetaTest/Average/MinReturn -173.532 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 29.9677 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.0498 +MetaTest/__unnamed_task__/AverageReturn -54.0498 +MetaTest/__unnamed_task__/Iteration 173 +MetaTest/__unnamed_task__/MaxReturn -16.2336 +MetaTest/__unnamed_task__/MinReturn -173.532 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 29.9677 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.352e+06 +__unnamed_task__/AverageDiscountedReturn -29.1233 +__unnamed_task__/AverageReturn -56.9754 +__unnamed_task__/Iteration 173 +__unnamed_task__/MaxReturn -21.7759 +__unnamed_task__/MinReturn -178.944 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 23.9541 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 02:27:14 | [maml_trainer] epoch #174 | Sampling for adapation and meta-testing... +2025-04-07 02:31:18 | [maml_trainer] epoch #174 | Finished meta-testing... +2025-04-07 02:31:18 | [maml_trainer] epoch #174 | Saving snapshot... +2025-04-07 02:31:39 | [maml_trainer] epoch #174 | Saved +2025-04-07 02:31:39 | [maml_trainer] epoch #174 | Time 294743.68 s +2025-04-07 02:31:39 | [maml_trainer] epoch #174 | EpochTime 1684.44 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.2745 +Average/AverageReturn -53.3917 +Average/Iteration 174 +Average/MaxReturn -35.5313 +Average/MinReturn -160.129 +Average/NumEpisodes 120 +Average/StdReturn 17.3355 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88269 +GaussianMLPPolicy/KLAfter 0.00205254 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.42372e-05 +GaussianMLPPolicy/LossBefore 7.05322e-09 +GaussianMLPPolicy/dLoss -4.42302e-05 +Iteration 174 +MetaTest/Average/AverageDiscountedReturn -49.5531 +MetaTest/Average/AverageReturn -49.5531 +MetaTest/Average/Iteration 174 +MetaTest/Average/MaxReturn -42.2303 +MetaTest/Average/MinReturn -64.9637 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.92614 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5531 +MetaTest/__unnamed_task__/AverageReturn -49.5531 +MetaTest/__unnamed_task__/Iteration 174 +MetaTest/__unnamed_task__/MaxReturn -42.2303 +MetaTest/__unnamed_task__/MinReturn -64.9637 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.92614 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.4e+06 +__unnamed_task__/AverageDiscountedReturn -28.2745 +__unnamed_task__/AverageReturn -53.3917 +__unnamed_task__/Iteration 174 +__unnamed_task__/MaxReturn -35.5313 +__unnamed_task__/MinReturn -160.129 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.3355 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 02:55:17 | [maml_trainer] epoch #175 | Sampling for adapation and meta-testing... +2025-04-07 02:59:15 | [maml_trainer] epoch #175 | Finished meta-testing... +2025-04-07 02:59:15 | [maml_trainer] epoch #175 | Saving snapshot... +2025-04-07 02:59:37 | [maml_trainer] epoch #175 | Saved +2025-04-07 02:59:37 | [maml_trainer] epoch #175 | Time 296421.10 s +2025-04-07 02:59:37 | [maml_trainer] epoch #175 | EpochTime 1677.42 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.5553 +Average/AverageReturn -55.9232 +Average/Iteration 175 +Average/MaxReturn -39.7624 +Average/MinReturn -169.222 +Average/NumEpisodes 120 +Average/StdReturn 23.2932 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88229 +GaussianMLPPolicy/KLAfter 0.00211989 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.2347e-05 +GaussianMLPPolicy/LossBefore 1.98683e-11 +GaussianMLPPolicy/dLoss 3.23471e-05 +Iteration 175 +MetaTest/Average/AverageDiscountedReturn -58.5743 +MetaTest/Average/AverageReturn -58.5743 +MetaTest/Average/Iteration 175 +MetaTest/Average/MaxReturn -39.2082 +MetaTest/Average/MinReturn -143.108 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 28.755 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.5743 +MetaTest/__unnamed_task__/AverageReturn -58.5743 +MetaTest/__unnamed_task__/Iteration 175 +MetaTest/__unnamed_task__/MaxReturn -39.2082 +MetaTest/__unnamed_task__/MinReturn -143.108 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 28.755 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.448e+06 +__unnamed_task__/AverageDiscountedReturn -28.5553 +__unnamed_task__/AverageReturn -55.9232 +__unnamed_task__/Iteration 175 +__unnamed_task__/MaxReturn -39.7624 +__unnamed_task__/MinReturn -169.222 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 23.2932 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 03:23:38 | [maml_trainer] epoch #176 | Sampling for adapation and meta-testing... +2025-04-07 03:27:39 | [maml_trainer] epoch #176 | Finished meta-testing... +2025-04-07 03:27:39 | [maml_trainer] epoch #176 | Saving snapshot... +2025-04-07 03:28:01 | [maml_trainer] epoch #176 | Saved +2025-04-07 03:28:01 | [maml_trainer] epoch #176 | Time 298125.52 s +2025-04-07 03:28:01 | [maml_trainer] epoch #176 | EpochTime 1704.41 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.3029 +Average/AverageReturn -49.5938 +Average/Iteration 176 +Average/MaxReturn -38.7661 +Average/MinReturn -95.9797 +Average/NumEpisodes 120 +Average/StdReturn 7.43963 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88222 +GaussianMLPPolicy/KLAfter 0.00214522 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.87041e-05 +GaussianMLPPolicy/LossBefore -1.42654e-08 +GaussianMLPPolicy/dLoss -7.87184e-05 +Iteration 176 +MetaTest/Average/AverageDiscountedReturn -52.9837 +MetaTest/Average/AverageReturn -52.9837 +MetaTest/Average/Iteration 176 +MetaTest/Average/MaxReturn -42.1409 +MetaTest/Average/MinReturn -88.4789 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.478 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.9837 +MetaTest/__unnamed_task__/AverageReturn -52.9837 +MetaTest/__unnamed_task__/Iteration 176 +MetaTest/__unnamed_task__/MaxReturn -42.1409 +MetaTest/__unnamed_task__/MinReturn -88.4789 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.478 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.496e+06 +__unnamed_task__/AverageDiscountedReturn -27.3029 +__unnamed_task__/AverageReturn -49.5938 +__unnamed_task__/Iteration 176 +__unnamed_task__/MaxReturn -38.7661 +__unnamed_task__/MinReturn -95.9797 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.43963 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 03:51:49 | [maml_trainer] epoch #177 | Sampling for adapation and meta-testing... +2025-04-07 03:55:49 | [maml_trainer] epoch #177 | Finished meta-testing... +2025-04-07 03:55:49 | [maml_trainer] epoch #177 | Saving snapshot... +2025-04-07 03:56:10 | [maml_trainer] epoch #177 | Saved +2025-04-07 03:56:10 | [maml_trainer] epoch #177 | Time 299814.90 s +2025-04-07 03:56:10 | [maml_trainer] epoch #177 | EpochTime 1689.38 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2065 +Average/AverageReturn -49.9451 +Average/Iteration 177 +Average/MaxReturn -38.942 +Average/MinReturn -133.38 +Average/NumEpisodes 120 +Average/StdReturn 11.7083 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88345 +GaussianMLPPolicy/KLAfter 0.00095355 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.46566e-05 +GaussianMLPPolicy/LossBefore -5.5631e-09 +GaussianMLPPolicy/dLoss 6.4651e-05 +Iteration 177 +MetaTest/Average/AverageDiscountedReturn -54.1295 +MetaTest/Average/AverageReturn -54.1295 +MetaTest/Average/Iteration 177 +MetaTest/Average/MaxReturn -43.1412 +MetaTest/Average/MinReturn -122.128 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.0082 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1295 +MetaTest/__unnamed_task__/AverageReturn -54.1295 +MetaTest/__unnamed_task__/Iteration 177 +MetaTest/__unnamed_task__/MaxReturn -43.1412 +MetaTest/__unnamed_task__/MinReturn -122.128 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.0082 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.544e+06 +__unnamed_task__/AverageDiscountedReturn -27.2065 +__unnamed_task__/AverageReturn -49.9451 +__unnamed_task__/Iteration 177 +__unnamed_task__/MaxReturn -38.942 +__unnamed_task__/MinReturn -133.38 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.7083 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 04:20:22 | [maml_trainer] epoch #178 | Sampling for adapation and meta-testing... +2025-04-07 04:24:22 | [maml_trainer] epoch #178 | Finished meta-testing... +2025-04-07 04:24:22 | [maml_trainer] epoch #178 | Saving snapshot... +2025-04-07 04:24:43 | [maml_trainer] epoch #178 | Saved +2025-04-07 04:24:43 | [maml_trainer] epoch #178 | Time 301527.82 s +2025-04-07 04:24:43 | [maml_trainer] epoch #178 | EpochTime 1712.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.458 +Average/AverageReturn -50.1993 +Average/Iteration 178 +Average/MaxReturn -39.3152 +Average/MinReturn -130.173 +Average/NumEpisodes 120 +Average/StdReturn 9.72753 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8839 +GaussianMLPPolicy/KLAfter 0.00145505 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.02652e-05 +GaussianMLPPolicy/LossBefore 6.75519e-10 +GaussianMLPPolicy/dLoss -4.02645e-05 +Iteration 178 +MetaTest/Average/AverageDiscountedReturn -50.3102 +MetaTest/Average/AverageReturn -50.3102 +MetaTest/Average/Iteration 178 +MetaTest/Average/MaxReturn -40.5086 +MetaTest/Average/MinReturn -70.8456 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.33982 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3102 +MetaTest/__unnamed_task__/AverageReturn -50.3102 +MetaTest/__unnamed_task__/Iteration 178 +MetaTest/__unnamed_task__/MaxReturn -40.5086 +MetaTest/__unnamed_task__/MinReturn -70.8456 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.33982 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.592e+06 +__unnamed_task__/AverageDiscountedReturn -27.458 +__unnamed_task__/AverageReturn -50.1993 +__unnamed_task__/Iteration 178 +__unnamed_task__/MaxReturn -39.3152 +__unnamed_task__/MinReturn -130.173 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.72753 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 04:48:55 | [maml_trainer] epoch #179 | Sampling for adapation and meta-testing... +2025-04-07 04:52:54 | [maml_trainer] epoch #179 | Finished meta-testing... +2025-04-07 04:52:54 | [maml_trainer] epoch #179 | Saving snapshot... +2025-04-07 04:53:15 | [maml_trainer] epoch #179 | Saved +2025-04-07 04:53:15 | [maml_trainer] epoch #179 | Time 303239.57 s +2025-04-07 04:53:15 | [maml_trainer] epoch #179 | EpochTime 1711.74 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.7507 +Average/AverageReturn -45.3876 +Average/Iteration 179 +Average/MaxReturn 498.814 +Average/MinReturn -99.2032 +Average/NumEpisodes 120 +Average/StdReturn 50.3695 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88369 +GaussianMLPPolicy/KLAfter 0.0021785 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.96145e-05 +GaussianMLPPolicy/LossBefore 7.30654e-09 +GaussianMLPPolicy/dLoss 4.96218e-05 +Iteration 179 +MetaTest/Average/AverageDiscountedReturn -55.6735 +MetaTest/Average/AverageReturn -55.6735 +MetaTest/Average/Iteration 179 +MetaTest/Average/MaxReturn -44.2199 +MetaTest/Average/MinReturn -176.047 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 27.8312 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.6735 +MetaTest/__unnamed_task__/AverageReturn -55.6735 +MetaTest/__unnamed_task__/Iteration 179 +MetaTest/__unnamed_task__/MaxReturn -44.2199 +MetaTest/__unnamed_task__/MinReturn -176.047 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 27.8312 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.64e+06 +__unnamed_task__/AverageDiscountedReturn -26.7507 +__unnamed_task__/AverageReturn -45.3876 +__unnamed_task__/Iteration 179 +__unnamed_task__/MaxReturn 498.814 +__unnamed_task__/MinReturn -99.2032 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 50.3695 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 05:17:27 | [maml_trainer] epoch #180 | Sampling for adapation and meta-testing... +2025-04-07 05:21:26 | [maml_trainer] epoch #180 | Finished meta-testing... +2025-04-07 05:21:26 | [maml_trainer] epoch #180 | Saving snapshot... +2025-04-07 05:21:47 | [maml_trainer] epoch #180 | Saved +2025-04-07 05:21:47 | [maml_trainer] epoch #180 | Time 304951.54 s +2025-04-07 05:21:47 | [maml_trainer] epoch #180 | EpochTime 1711.97 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.1193 +Average/AverageReturn -49.059 +Average/Iteration 180 +Average/MaxReturn -40.892 +Average/MinReturn -89.3168 +Average/NumEpisodes 120 +Average/StdReturn 6.25805 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88436 +GaussianMLPPolicy/KLAfter 0.00132284 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.44293e-05 +GaussianMLPPolicy/LossBefore -1.13249e-08 +GaussianMLPPolicy/dLoss -2.44406e-05 +Iteration 180 +MetaTest/Average/AverageDiscountedReturn -48.4498 +MetaTest/Average/AverageReturn -48.4498 +MetaTest/Average/Iteration 180 +MetaTest/Average/MaxReturn -42.7588 +MetaTest/Average/MinReturn -66.512 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.11066 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4498 +MetaTest/__unnamed_task__/AverageReturn -48.4498 +MetaTest/__unnamed_task__/Iteration 180 +MetaTest/__unnamed_task__/MaxReturn -42.7588 +MetaTest/__unnamed_task__/MinReturn -66.512 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.11066 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.688e+06 +__unnamed_task__/AverageDiscountedReturn -27.1193 +__unnamed_task__/AverageReturn -49.059 +__unnamed_task__/Iteration 180 +__unnamed_task__/MaxReturn -40.892 +__unnamed_task__/MinReturn -89.3168 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.25805 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 05:45:39 | [maml_trainer] epoch #181 | Sampling for adapation and meta-testing... +2025-04-07 05:49:37 | [maml_trainer] epoch #181 | Finished meta-testing... +2025-04-07 05:49:37 | [maml_trainer] epoch #181 | Saving snapshot... +2025-04-07 05:49:58 | [maml_trainer] epoch #181 | Saved +2025-04-07 05:49:58 | [maml_trainer] epoch #181 | Time 306642.48 s +2025-04-07 05:49:58 | [maml_trainer] epoch #181 | EpochTime 1690.93 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.4349 +Average/AverageReturn -49.9102 +Average/Iteration 181 +Average/MaxReturn -38.2062 +Average/MinReturn -144.599 +Average/NumEpisodes 120 +Average/StdReturn 10.8765 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88504 +GaussianMLPPolicy/KLAfter 0.00170528 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.71667e-05 +GaussianMLPPolicy/LossBefore -1.23978e-08 +GaussianMLPPolicy/dLoss 6.71543e-05 +Iteration 181 +MetaTest/Average/AverageDiscountedReturn -61.0889 +MetaTest/Average/AverageReturn -61.0889 +MetaTest/Average/Iteration 181 +MetaTest/Average/MaxReturn -39.6333 +MetaTest/Average/MinReturn -151.795 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 30.3366 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -61.0889 +MetaTest/__unnamed_task__/AverageReturn -61.0889 +MetaTest/__unnamed_task__/Iteration 181 +MetaTest/__unnamed_task__/MaxReturn -39.6333 +MetaTest/__unnamed_task__/MinReturn -151.795 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 30.3366 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.736e+06 +__unnamed_task__/AverageDiscountedReturn -27.4349 +__unnamed_task__/AverageReturn -49.9102 +__unnamed_task__/Iteration 181 +__unnamed_task__/MaxReturn -38.2062 +__unnamed_task__/MinReturn -144.599 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.8765 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 06:13:42 | [maml_trainer] epoch #182 | Sampling for adapation and meta-testing... +2025-04-07 06:17:40 | [maml_trainer] epoch #182 | Finished meta-testing... +2025-04-07 06:17:40 | [maml_trainer] epoch #182 | Saving snapshot... +2025-04-07 06:18:01 | [maml_trainer] epoch #182 | Saved +2025-04-07 06:18:01 | [maml_trainer] epoch #182 | Time 308325.22 s +2025-04-07 06:18:01 | [maml_trainer] epoch #182 | EpochTime 1682.74 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2474 +Average/AverageReturn -49.1748 +Average/Iteration 182 +Average/MaxReturn -41.1177 +Average/MinReturn -70.4861 +Average/NumEpisodes 120 +Average/StdReturn 5.44592 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88528 +GaussianMLPPolicy/KLAfter 0.00173274 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.35161e-06 +GaussianMLPPolicy/LossBefore 7.15256e-09 +GaussianMLPPolicy/dLoss 3.35876e-06 +Iteration 182 +MetaTest/Average/AverageDiscountedReturn -51.5908 +MetaTest/Average/AverageReturn -51.5908 +MetaTest/Average/Iteration 182 +MetaTest/Average/MaxReturn -43.1335 +MetaTest/Average/MinReturn -62.6053 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.79998 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5908 +MetaTest/__unnamed_task__/AverageReturn -51.5908 +MetaTest/__unnamed_task__/Iteration 182 +MetaTest/__unnamed_task__/MaxReturn -43.1335 +MetaTest/__unnamed_task__/MinReturn -62.6053 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.79998 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.784e+06 +__unnamed_task__/AverageDiscountedReturn -27.2474 +__unnamed_task__/AverageReturn -49.1748 +__unnamed_task__/Iteration 182 +__unnamed_task__/MaxReturn -41.1177 +__unnamed_task__/MinReturn -70.4861 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.44592 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 06:42:05 | [maml_trainer] epoch #183 | Sampling for adapation and meta-testing... +2025-04-07 06:46:08 | [maml_trainer] epoch #183 | Finished meta-testing... +2025-04-07 06:46:08 | [maml_trainer] epoch #183 | Saving snapshot... +2025-04-07 06:46:29 | [maml_trainer] epoch #183 | Saved +2025-04-07 06:46:29 | [maml_trainer] epoch #183 | Time 310033.29 s +2025-04-07 06:46:29 | [maml_trainer] epoch #183 | EpochTime 1708.07 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6977 +Average/AverageReturn -50.3764 +Average/Iteration 183 +Average/MaxReturn -39.9212 +Average/MinReturn -77.6768 +Average/NumEpisodes 120 +Average/StdReturn 6.07879 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88432 +GaussianMLPPolicy/KLAfter 0.00221216 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.70467e-05 +GaussianMLPPolicy/LossBefore 9.02017e-09 +GaussianMLPPolicy/dLoss 6.70557e-05 +Iteration 183 +MetaTest/Average/AverageDiscountedReturn -50.5177 +MetaTest/Average/AverageReturn -50.5177 +MetaTest/Average/Iteration 183 +MetaTest/Average/MaxReturn -43.1634 +MetaTest/Average/MinReturn -64.8364 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.36867 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5177 +MetaTest/__unnamed_task__/AverageReturn -50.5177 +MetaTest/__unnamed_task__/Iteration 183 +MetaTest/__unnamed_task__/MaxReturn -43.1634 +MetaTest/__unnamed_task__/MinReturn -64.8364 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.36867 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.832e+06 +__unnamed_task__/AverageDiscountedReturn -27.6977 +__unnamed_task__/AverageReturn -50.3764 +__unnamed_task__/Iteration 183 +__unnamed_task__/MaxReturn -39.9212 +__unnamed_task__/MinReturn -77.6768 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.07879 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 07:10:41 | [maml_trainer] epoch #184 | Sampling for adapation and meta-testing... +2025-04-07 07:14:41 | [maml_trainer] epoch #184 | Finished meta-testing... +2025-04-07 07:14:41 | [maml_trainer] epoch #184 | Saving snapshot... +2025-04-07 07:15:02 | [maml_trainer] epoch #184 | Saved +2025-04-07 07:15:02 | [maml_trainer] epoch #184 | Time 311746.44 s +2025-04-07 07:15:02 | [maml_trainer] epoch #184 | EpochTime 1713.15 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6413 +Average/AverageReturn -50.3122 +Average/Iteration 184 +Average/MaxReturn -42.5313 +Average/MinReturn -66.1257 +Average/NumEpisodes 120 +Average/StdReturn 5.03394 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.88151 +GaussianMLPPolicy/KLAfter 0.00117574 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.4811e-05 +GaussianMLPPolicy/LossBefore 3.3776e-09 +GaussianMLPPolicy/dLoss -2.48076e-05 +Iteration 184 +MetaTest/Average/AverageDiscountedReturn -51.5448 +MetaTest/Average/AverageReturn -51.5448 +MetaTest/Average/Iteration 184 +MetaTest/Average/MaxReturn -44.4458 +MetaTest/Average/MinReturn -65.8046 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.97126 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5448 +MetaTest/__unnamed_task__/AverageReturn -51.5448 +MetaTest/__unnamed_task__/Iteration 184 +MetaTest/__unnamed_task__/MaxReturn -44.4458 +MetaTest/__unnamed_task__/MinReturn -65.8046 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.97126 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.88e+06 +__unnamed_task__/AverageDiscountedReturn -27.6413 +__unnamed_task__/AverageReturn -50.3122 +__unnamed_task__/Iteration 184 +__unnamed_task__/MaxReturn -42.5313 +__unnamed_task__/MinReturn -66.1257 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.03394 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 07:39:17 | [maml_trainer] epoch #185 | Sampling for adapation and meta-testing... +2025-04-07 07:43:19 | [maml_trainer] epoch #185 | Finished meta-testing... +2025-04-07 07:43:19 | [maml_trainer] epoch #185 | Saving snapshot... +2025-04-07 07:43:39 | [maml_trainer] epoch #185 | Saved +2025-04-07 07:43:39 | [maml_trainer] epoch #185 | Time 313463.84 s +2025-04-07 07:43:39 | [maml_trainer] epoch #185 | EpochTime 1717.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.7723 +Average/AverageReturn -50.7196 +Average/Iteration 185 +Average/MaxReturn -41.712 +Average/MinReturn -70.955 +Average/NumEpisodes 120 +Average/StdReturn 5.86679 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8767 +GaussianMLPPolicy/KLAfter 0.00139659 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.33665e-05 +GaussianMLPPolicy/LossBefore -1.20401e-08 +GaussianMLPPolicy/dLoss 1.33545e-05 +Iteration 185 +MetaTest/Average/AverageDiscountedReturn -50.9746 +MetaTest/Average/AverageReturn -50.9746 +MetaTest/Average/Iteration 185 +MetaTest/Average/MaxReturn -43.3642 +MetaTest/Average/MinReturn -61.0086 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.00824 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9746 +MetaTest/__unnamed_task__/AverageReturn -50.9746 +MetaTest/__unnamed_task__/Iteration 185 +MetaTest/__unnamed_task__/MaxReturn -43.3642 +MetaTest/__unnamed_task__/MinReturn -61.0086 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.00824 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.928e+06 +__unnamed_task__/AverageDiscountedReturn -27.7723 +__unnamed_task__/AverageReturn -50.7196 +__unnamed_task__/Iteration 185 +__unnamed_task__/MaxReturn -41.712 +__unnamed_task__/MinReturn -70.955 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.86679 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 08:07:50 | [maml_trainer] epoch #186 | Sampling for adapation and meta-testing... +2025-04-07 08:11:48 | [maml_trainer] epoch #186 | Finished meta-testing... +2025-04-07 08:11:48 | [maml_trainer] epoch #186 | Saving snapshot... +2025-04-07 08:12:09 | [maml_trainer] epoch #186 | Saved +2025-04-07 08:12:09 | [maml_trainer] epoch #186 | Time 315173.48 s +2025-04-07 08:12:09 | [maml_trainer] epoch #186 | EpochTime 1709.64 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9677 +Average/AverageReturn -51.2916 +Average/Iteration 186 +Average/MaxReturn -40.6604 +Average/MinReturn -75.8067 +Average/NumEpisodes 120 +Average/StdReturn 5.95813 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.87338 +GaussianMLPPolicy/KLAfter 0.0013074 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.63821e-05 +GaussianMLPPolicy/LossBefore 1.59343e-08 +GaussianMLPPolicy/dLoss 2.63981e-05 +Iteration 186 +MetaTest/Average/AverageDiscountedReturn -54.7658 +MetaTest/Average/AverageReturn -54.7658 +MetaTest/Average/Iteration 186 +MetaTest/Average/MaxReturn -43.4017 +MetaTest/Average/MinReturn -96.1089 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.6323 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.7658 +MetaTest/__unnamed_task__/AverageReturn -54.7658 +MetaTest/__unnamed_task__/Iteration 186 +MetaTest/__unnamed_task__/MaxReturn -43.4017 +MetaTest/__unnamed_task__/MinReturn -96.1089 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.6323 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 8.976e+06 +__unnamed_task__/AverageDiscountedReturn -27.9677 +__unnamed_task__/AverageReturn -51.2916 +__unnamed_task__/Iteration 186 +__unnamed_task__/MaxReturn -40.6604 +__unnamed_task__/MinReturn -75.8067 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.95813 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 08:36:15 | [maml_trainer] epoch #187 | Sampling for adapation and meta-testing... +2025-04-07 08:40:16 | [maml_trainer] epoch #187 | Finished meta-testing... +2025-04-07 08:40:16 | [maml_trainer] epoch #187 | Saving snapshot... +2025-04-07 08:40:35 | [maml_trainer] epoch #187 | Saved +2025-04-07 08:40:35 | [maml_trainer] epoch #187 | Time 316879.92 s +2025-04-07 08:40:35 | [maml_trainer] epoch #187 | EpochTime 1706.44 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1865 +Average/AverageReturn -51.8656 +Average/Iteration 187 +Average/MaxReturn -42.7827 +Average/MinReturn -68.8682 +Average/NumEpisodes 120 +Average/StdReturn 5.37175 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.86942 +GaussianMLPPolicy/KLAfter 0.00208942 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.99424e-06 +GaussianMLPPolicy/LossBefore -1.07288e-09 +GaussianMLPPolicy/dLoss -5.99531e-06 +Iteration 187 +MetaTest/Average/AverageDiscountedReturn -51.6632 +MetaTest/Average/AverageReturn -51.6632 +MetaTest/Average/Iteration 187 +MetaTest/Average/MaxReturn -45.8759 +MetaTest/Average/MinReturn -64.2561 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.28418 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6632 +MetaTest/__unnamed_task__/AverageReturn -51.6632 +MetaTest/__unnamed_task__/Iteration 187 +MetaTest/__unnamed_task__/MaxReturn -45.8759 +MetaTest/__unnamed_task__/MinReturn -64.2561 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.28418 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.024e+06 +__unnamed_task__/AverageDiscountedReturn -28.1865 +__unnamed_task__/AverageReturn -51.8656 +__unnamed_task__/Iteration 187 +__unnamed_task__/MaxReturn -42.7827 +__unnamed_task__/MinReturn -68.8682 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.37175 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 09:04:30 | [maml_trainer] epoch #188 | Sampling for adapation and meta-testing... +2025-04-07 09:08:31 | [maml_trainer] epoch #188 | Finished meta-testing... +2025-04-07 09:08:31 | [maml_trainer] epoch #188 | Saving snapshot... +2025-04-07 09:08:52 | [maml_trainer] epoch #188 | Saved +2025-04-07 09:08:52 | [maml_trainer] epoch #188 | Time 318576.82 s +2025-04-07 09:08:52 | [maml_trainer] epoch #188 | EpochTime 1696.89 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8087 +Average/AverageReturn -51.0128 +Average/Iteration 188 +Average/MaxReturn -40.6187 +Average/MinReturn -92.8194 +Average/NumEpisodes 120 +Average/StdReturn 6.93975 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.86592 +GaussianMLPPolicy/KLAfter 0.00316045 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.5413e-05 +GaussianMLPPolicy/LossBefore -2.26498e-09 +GaussianMLPPolicy/dLoss 2.54108e-05 +Iteration 188 +MetaTest/Average/AverageDiscountedReturn -55.5372 +MetaTest/Average/AverageReturn -55.5372 +MetaTest/Average/Iteration 188 +MetaTest/Average/MaxReturn -43.3031 +MetaTest/Average/MinReturn -78.2202 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.48342 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.5372 +MetaTest/__unnamed_task__/AverageReturn -55.5372 +MetaTest/__unnamed_task__/Iteration 188 +MetaTest/__unnamed_task__/MaxReturn -43.3031 +MetaTest/__unnamed_task__/MinReturn -78.2202 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.48342 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.072e+06 +__unnamed_task__/AverageDiscountedReturn -27.8087 +__unnamed_task__/AverageReturn -51.0128 +__unnamed_task__/Iteration 188 +__unnamed_task__/MaxReturn -40.6187 +__unnamed_task__/MinReturn -92.8194 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.93975 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 09:32:41 | [maml_trainer] epoch #189 | Sampling for adapation and meta-testing... +2025-04-07 09:36:38 | [maml_trainer] epoch #189 | Finished meta-testing... +2025-04-07 09:36:38 | [maml_trainer] epoch #189 | Saving snapshot... +2025-04-07 09:36:58 | [maml_trainer] epoch #189 | Saved +2025-04-07 09:36:58 | [maml_trainer] epoch #189 | Time 320262.93 s +2025-04-07 09:36:58 | [maml_trainer] epoch #189 | EpochTime 1686.11 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0669 +Average/AverageReturn -51.1385 +Average/Iteration 189 +Average/MaxReturn -43.1279 +Average/MinReturn -71.5291 +Average/NumEpisodes 120 +Average/StdReturn 4.79666 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.86127 +GaussianMLPPolicy/KLAfter 0.00228214 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.99456e-05 +GaussianMLPPolicy/LossBefore -7.35124e-09 +GaussianMLPPolicy/dLoss -3.9953e-05 +Iteration 189 +MetaTest/Average/AverageDiscountedReturn -49.8685 +MetaTest/Average/AverageReturn -49.8685 +MetaTest/Average/Iteration 189 +MetaTest/Average/MaxReturn -44.4102 +MetaTest/Average/MinReturn -61.8812 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.13516 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8685 +MetaTest/__unnamed_task__/AverageReturn -49.8685 +MetaTest/__unnamed_task__/Iteration 189 +MetaTest/__unnamed_task__/MaxReturn -44.4102 +MetaTest/__unnamed_task__/MinReturn -61.8812 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.13516 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.12e+06 +__unnamed_task__/AverageDiscountedReturn -28.0669 +__unnamed_task__/AverageReturn -51.1385 +__unnamed_task__/Iteration 189 +__unnamed_task__/MaxReturn -43.1279 +__unnamed_task__/MinReturn -71.5291 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.79666 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 10:00:54 | [maml_trainer] epoch #190 | Sampling for adapation and meta-testing... +2025-04-07 10:04:50 | [maml_trainer] epoch #190 | Finished meta-testing... +2025-04-07 10:04:50 | [maml_trainer] epoch #190 | Saving snapshot... +2025-04-07 10:05:11 | [maml_trainer] epoch #190 | Saved +2025-04-07 10:05:11 | [maml_trainer] epoch #190 | Time 321955.61 s +2025-04-07 10:05:11 | [maml_trainer] epoch #190 | EpochTime 1692.68 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2081 +Average/AverageReturn -51.9656 +Average/Iteration 190 +Average/MaxReturn -43.1978 +Average/MinReturn -78.6175 +Average/NumEpisodes 120 +Average/StdReturn 5.93177 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.85651 +GaussianMLPPolicy/KLAfter 0.00337287 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.81791e-06 +GaussianMLPPolicy/LossBefore 1.90735e-09 +GaussianMLPPolicy/dLoss 2.81982e-06 +Iteration 190 +MetaTest/Average/AverageDiscountedReturn -51.3012 +MetaTest/Average/AverageReturn -51.3012 +MetaTest/Average/Iteration 190 +MetaTest/Average/MaxReturn -44.0593 +MetaTest/Average/MinReturn -64.8261 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.54341 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3012 +MetaTest/__unnamed_task__/AverageReturn -51.3012 +MetaTest/__unnamed_task__/Iteration 190 +MetaTest/__unnamed_task__/MaxReturn -44.0593 +MetaTest/__unnamed_task__/MinReturn -64.8261 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.54341 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.168e+06 +__unnamed_task__/AverageDiscountedReturn -28.2081 +__unnamed_task__/AverageReturn -51.9656 +__unnamed_task__/Iteration 190 +__unnamed_task__/MaxReturn -43.1978 +__unnamed_task__/MinReturn -78.6175 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.93177 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 10:28:41 | [maml_trainer] epoch #191 | Sampling for adapation and meta-testing... +2025-04-07 10:32:36 | [maml_trainer] epoch #191 | Finished meta-testing... +2025-04-07 10:32:36 | [maml_trainer] epoch #191 | Saving snapshot... +2025-04-07 10:32:57 | [maml_trainer] epoch #191 | Saved +2025-04-07 10:32:57 | [maml_trainer] epoch #191 | Time 323621.45 s +2025-04-07 10:32:57 | [maml_trainer] epoch #191 | EpochTime 1665.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0916 +Average/AverageReturn -51.0378 +Average/Iteration 191 +Average/MaxReturn -43.1106 +Average/MinReturn -71.3202 +Average/NumEpisodes 120 +Average/StdReturn 5.38777 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.85223 +GaussianMLPPolicy/KLAfter 0.00273034 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000144697 +GaussianMLPPolicy/LossBefore -1.07686e-08 +GaussianMLPPolicy/dLoss -0.000144707 +Iteration 191 +MetaTest/Average/AverageDiscountedReturn -51.5788 +MetaTest/Average/AverageReturn -51.5788 +MetaTest/Average/Iteration 191 +MetaTest/Average/MaxReturn -43.4679 +MetaTest/Average/MinReturn -71.0218 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.24369 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5788 +MetaTest/__unnamed_task__/AverageReturn -51.5788 +MetaTest/__unnamed_task__/Iteration 191 +MetaTest/__unnamed_task__/MaxReturn -43.4679 +MetaTest/__unnamed_task__/MinReturn -71.0218 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.24369 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.216e+06 +__unnamed_task__/AverageDiscountedReturn -28.0916 +__unnamed_task__/AverageReturn -51.0378 +__unnamed_task__/Iteration 191 +__unnamed_task__/MaxReturn -43.1106 +__unnamed_task__/MinReturn -71.3202 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.38777 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 10:56:22 | [maml_trainer] epoch #192 | Sampling for adapation and meta-testing... +2025-04-07 11:00:17 | [maml_trainer] epoch #192 | Finished meta-testing... +2025-04-07 11:00:17 | [maml_trainer] epoch #192 | Saving snapshot... +2025-04-07 11:00:37 | [maml_trainer] epoch #192 | Saved +2025-04-07 11:00:37 | [maml_trainer] epoch #192 | Time 325281.68 s +2025-04-07 11:00:37 | [maml_trainer] epoch #192 | EpochTime 1660.22 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.955 +Average/AverageReturn -53.795 +Average/Iteration 192 +Average/MaxReturn -44.0459 +Average/MinReturn -92.3731 +Average/NumEpisodes 120 +Average/StdReturn 7.60594 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84878 +GaussianMLPPolicy/KLAfter 0.00389809 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.13634e-06 +GaussianMLPPolicy/LossBefore 1.27554e-08 +GaussianMLPPolicy/dLoss -7.12359e-06 +Iteration 192 +MetaTest/Average/AverageDiscountedReturn -57.4926 +MetaTest/Average/AverageReturn -57.4926 +MetaTest/Average/Iteration 192 +MetaTest/Average/MaxReturn -47.45 +MetaTest/Average/MinReturn -78.7805 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.74221 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.4926 +MetaTest/__unnamed_task__/AverageReturn -57.4926 +MetaTest/__unnamed_task__/Iteration 192 +MetaTest/__unnamed_task__/MaxReturn -47.45 +MetaTest/__unnamed_task__/MinReturn -78.7805 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.74221 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.264e+06 +__unnamed_task__/AverageDiscountedReturn -28.955 +__unnamed_task__/AverageReturn -53.795 +__unnamed_task__/Iteration 192 +__unnamed_task__/MaxReturn -44.0459 +__unnamed_task__/MinReturn -92.3731 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.60594 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 11:24:26 | [maml_trainer] epoch #193 | Sampling for adapation and meta-testing... +2025-04-07 11:28:22 | [maml_trainer] epoch #193 | Finished meta-testing... +2025-04-07 11:28:22 | [maml_trainer] epoch #193 | Saving snapshot... +2025-04-07 11:28:43 | [maml_trainer] epoch #193 | Saved +2025-04-07 11:28:43 | [maml_trainer] epoch #193 | Time 326967.13 s +2025-04-07 11:28:43 | [maml_trainer] epoch #193 | EpochTime 1685.45 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8075 +Average/AverageReturn -52.7665 +Average/Iteration 193 +Average/MaxReturn -41.5578 +Average/MinReturn -86.8922 +Average/NumEpisodes 120 +Average/StdReturn 7.40849 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84651 +GaussianMLPPolicy/KLAfter 0.00412446 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000230391 +GaussianMLPPolicy/LossBefore -9.85463e-09 +GaussianMLPPolicy/dLoss 0.000230381 +Iteration 193 +MetaTest/Average/AverageDiscountedReturn -52.7811 +MetaTest/Average/AverageReturn -52.7811 +MetaTest/Average/Iteration 193 +MetaTest/Average/MaxReturn -45.8525 +MetaTest/Average/MinReturn -75.63 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.98761 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.7811 +MetaTest/__unnamed_task__/AverageReturn -52.7811 +MetaTest/__unnamed_task__/Iteration 193 +MetaTest/__unnamed_task__/MaxReturn -45.8525 +MetaTest/__unnamed_task__/MinReturn -75.63 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.98761 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.312e+06 +__unnamed_task__/AverageDiscountedReturn -28.8075 +__unnamed_task__/AverageReturn -52.7665 +__unnamed_task__/Iteration 193 +__unnamed_task__/MaxReturn -41.5578 +__unnamed_task__/MinReturn -86.8922 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.40849 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 11:52:20 | [maml_trainer] epoch #194 | Sampling for adapation and meta-testing... +2025-04-07 11:56:21 | [maml_trainer] epoch #194 | Finished meta-testing... +2025-04-07 11:56:21 | [maml_trainer] epoch #194 | Saving snapshot... +2025-04-07 11:56:43 | [maml_trainer] epoch #194 | Saved +2025-04-07 11:56:43 | [maml_trainer] epoch #194 | Time 328647.79 s +2025-04-07 11:56:43 | [maml_trainer] epoch #194 | EpochTime 1680.65 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.7539 +Average/AverageReturn -53.138 +Average/Iteration 194 +Average/MaxReturn -43.1875 +Average/MinReturn -110.267 +Average/NumEpisodes 120 +Average/StdReturn 8.541 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84512 +GaussianMLPPolicy/KLAfter 0.00386002 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.75022e-05 +GaussianMLPPolicy/LossBefore -2.14577e-09 +GaussianMLPPolicy/dLoss 6.75e-05 +Iteration 194 +MetaTest/Average/AverageDiscountedReturn -51.0582 +MetaTest/Average/AverageReturn -51.0582 +MetaTest/Average/Iteration 194 +MetaTest/Average/MaxReturn -45.8465 +MetaTest/Average/MinReturn -59.707 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.85687 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.0582 +MetaTest/__unnamed_task__/AverageReturn -51.0582 +MetaTest/__unnamed_task__/Iteration 194 +MetaTest/__unnamed_task__/MaxReturn -45.8465 +MetaTest/__unnamed_task__/MinReturn -59.707 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.85687 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.36e+06 +__unnamed_task__/AverageDiscountedReturn -28.7539 +__unnamed_task__/AverageReturn -53.138 +__unnamed_task__/Iteration 194 +__unnamed_task__/MaxReturn -43.1875 +__unnamed_task__/MinReturn -110.267 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.541 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 12:21:41 | [maml_trainer] epoch #195 | Sampling for adapation and meta-testing... +2025-04-07 12:25:52 | [maml_trainer] epoch #195 | Finished meta-testing... +2025-04-07 12:25:52 | [maml_trainer] epoch #195 | Saving snapshot... +2025-04-07 12:26:14 | [maml_trainer] epoch #195 | Saved +2025-04-07 12:26:14 | [maml_trainer] epoch #195 | Time 330418.21 s +2025-04-07 12:26:14 | [maml_trainer] epoch #195 | EpochTime 1770.42 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.9134 +Average/AverageReturn -53.4756 +Average/Iteration 195 +Average/MaxReturn -43.6285 +Average/MinReturn -72.2803 +Average/NumEpisodes 120 +Average/StdReturn 6.08137 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84452 +GaussianMLPPolicy/KLAfter 0.00291569 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.35984e-05 +GaussianMLPPolicy/LossBefore 2.88089e-08 +GaussianMLPPolicy/dLoss -7.35696e-05 +Iteration 195 +MetaTest/Average/AverageDiscountedReturn -52.6972 +MetaTest/Average/AverageReturn -52.6972 +MetaTest/Average/Iteration 195 +MetaTest/Average/MaxReturn -47.1704 +MetaTest/Average/MinReturn -71.794 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.43168 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6972 +MetaTest/__unnamed_task__/AverageReturn -52.6972 +MetaTest/__unnamed_task__/Iteration 195 +MetaTest/__unnamed_task__/MaxReturn -47.1704 +MetaTest/__unnamed_task__/MinReturn -71.794 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.43168 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.408e+06 +__unnamed_task__/AverageDiscountedReturn -28.9134 +__unnamed_task__/AverageReturn -53.4756 +__unnamed_task__/Iteration 195 +__unnamed_task__/MaxReturn -43.6285 +__unnamed_task__/MinReturn -72.2803 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.08137 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 12:51:02 | [maml_trainer] epoch #196 | Sampling for adapation and meta-testing... +2025-04-07 12:55:09 | [maml_trainer] epoch #196 | Finished meta-testing... +2025-04-07 12:55:09 | [maml_trainer] epoch #196 | Saving snapshot... +2025-04-07 12:55:31 | [maml_trainer] epoch #196 | Saved +2025-04-07 12:55:31 | [maml_trainer] epoch #196 | Time 332175.53 s +2025-04-07 12:55:31 | [maml_trainer] epoch #196 | EpochTime 1757.32 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.708 +Average/AverageReturn -52.6249 +Average/Iteration 196 +Average/MaxReturn -43.7213 +Average/MinReturn -69.3713 +Average/NumEpisodes 120 +Average/StdReturn 5.70168 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84444 +GaussianMLPPolicy/KLAfter 0.00165577 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.41152e-05 +GaussianMLPPolicy/LossBefore -2.66234e-09 +GaussianMLPPolicy/dLoss 3.41125e-05 +Iteration 196 +MetaTest/Average/AverageDiscountedReturn -52.5016 +MetaTest/Average/AverageReturn -52.5016 +MetaTest/Average/Iteration 196 +MetaTest/Average/MaxReturn -47.2407 +MetaTest/Average/MinReturn -67.4335 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.88921 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5016 +MetaTest/__unnamed_task__/AverageReturn -52.5016 +MetaTest/__unnamed_task__/Iteration 196 +MetaTest/__unnamed_task__/MaxReturn -47.2407 +MetaTest/__unnamed_task__/MinReturn -67.4335 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.88921 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.456e+06 +__unnamed_task__/AverageDiscountedReturn -28.708 +__unnamed_task__/AverageReturn -52.6249 +__unnamed_task__/Iteration 196 +__unnamed_task__/MaxReturn -43.7213 +__unnamed_task__/MinReturn -69.3713 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.70168 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 13:20:46 | [maml_trainer] epoch #197 | Sampling for adapation and meta-testing... +2025-04-07 13:24:51 | [maml_trainer] epoch #197 | Finished meta-testing... +2025-04-07 13:24:51 | [maml_trainer] epoch #197 | Saving snapshot... +2025-04-07 13:25:13 | [maml_trainer] epoch #197 | Saved +2025-04-07 13:25:13 | [maml_trainer] epoch #197 | Time 333957.22 s +2025-04-07 13:25:13 | [maml_trainer] epoch #197 | EpochTime 1781.69 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.2378 +Average/AverageReturn -53.6216 +Average/Iteration 197 +Average/MaxReturn -43.8425 +Average/MinReturn -86.6697 +Average/NumEpisodes 120 +Average/StdReturn 7.01038 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8435 +GaussianMLPPolicy/KLAfter 0.00279883 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000152728 +GaussianMLPPolicy/LossBefore 1.35104e-08 +GaussianMLPPolicy/dLoss 0.000152742 +Iteration 197 +MetaTest/Average/AverageDiscountedReturn -51.6581 +MetaTest/Average/AverageReturn -51.6581 +MetaTest/Average/Iteration 197 +MetaTest/Average/MaxReturn -46.5357 +MetaTest/Average/MinReturn -64.3894 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.60494 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6581 +MetaTest/__unnamed_task__/AverageReturn -51.6581 +MetaTest/__unnamed_task__/Iteration 197 +MetaTest/__unnamed_task__/MaxReturn -46.5357 +MetaTest/__unnamed_task__/MinReturn -64.3894 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.60494 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.504e+06 +__unnamed_task__/AverageDiscountedReturn -29.2378 +__unnamed_task__/AverageReturn -53.6216 +__unnamed_task__/Iteration 197 +__unnamed_task__/MaxReturn -43.8425 +__unnamed_task__/MinReturn -86.6697 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.01038 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 13:50:24 | [maml_trainer] epoch #198 | Sampling for adapation and meta-testing... +2025-04-07 13:54:34 | [maml_trainer] epoch #198 | Finished meta-testing... +2025-04-07 13:54:34 | [maml_trainer] epoch #198 | Saving snapshot... +2025-04-07 13:54:56 | [maml_trainer] epoch #198 | Saved +2025-04-07 13:54:56 | [maml_trainer] epoch #198 | Time 335740.00 s +2025-04-07 13:54:56 | [maml_trainer] epoch #198 | EpochTime 1782.77 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8711 +Average/AverageReturn -52.2828 +Average/Iteration 198 +Average/MaxReturn -43.4149 +Average/MinReturn -75.7644 +Average/NumEpisodes 120 +Average/StdReturn 5.88396 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84305 +GaussianMLPPolicy/KLAfter 0.00346998 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.16445e-05 +GaussianMLPPolicy/LossBefore 2.9405e-09 +GaussianMLPPolicy/dLoss -4.16416e-05 +Iteration 198 +MetaTest/Average/AverageDiscountedReturn -50.1976 +MetaTest/Average/AverageReturn -50.1976 +MetaTest/Average/Iteration 198 +MetaTest/Average/MaxReturn -42.2746 +MetaTest/Average/MinReturn -62.2885 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.65553 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1976 +MetaTest/__unnamed_task__/AverageReturn -50.1976 +MetaTest/__unnamed_task__/Iteration 198 +MetaTest/__unnamed_task__/MaxReturn -42.2746 +MetaTest/__unnamed_task__/MinReturn -62.2885 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.65553 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.552e+06 +__unnamed_task__/AverageDiscountedReturn -28.8711 +__unnamed_task__/AverageReturn -52.2828 +__unnamed_task__/Iteration 198 +__unnamed_task__/MaxReturn -43.4149 +__unnamed_task__/MinReturn -75.7644 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.88396 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 14:20:03 | [maml_trainer] epoch #199 | Sampling for adapation and meta-testing... +2025-04-07 14:24:18 | [maml_trainer] epoch #199 | Finished meta-testing... +2025-04-07 14:24:18 | [maml_trainer] epoch #199 | Saving snapshot... +2025-04-07 14:24:41 | [maml_trainer] epoch #199 | Saved +2025-04-07 14:24:41 | [maml_trainer] epoch #199 | Time 337525.52 s +2025-04-07 14:24:41 | [maml_trainer] epoch #199 | EpochTime 1785.52 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4649 +Average/AverageReturn -51.2174 +Average/Iteration 199 +Average/MaxReturn -44.2051 +Average/MinReturn -71.4766 +Average/NumEpisodes 120 +Average/StdReturn 4.68839 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84241 +GaussianMLPPolicy/KLAfter 0.00257656 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.48129e-05 +GaussianMLPPolicy/LossBefore 2.07822e-08 +GaussianMLPPolicy/dLoss 3.48337e-05 +Iteration 199 +MetaTest/Average/AverageDiscountedReturn -50.3631 +MetaTest/Average/AverageReturn -50.3631 +MetaTest/Average/Iteration 199 +MetaTest/Average/MaxReturn -45.2166 +MetaTest/Average/MinReturn -58.7806 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.39858 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3631 +MetaTest/__unnamed_task__/AverageReturn -50.3631 +MetaTest/__unnamed_task__/Iteration 199 +MetaTest/__unnamed_task__/MaxReturn -45.2166 +MetaTest/__unnamed_task__/MinReturn -58.7806 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.39858 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.6e+06 +__unnamed_task__/AverageDiscountedReturn -28.4649 +__unnamed_task__/AverageReturn -51.2174 +__unnamed_task__/Iteration 199 +__unnamed_task__/MaxReturn -44.2051 +__unnamed_task__/MinReturn -71.4766 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.68839 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 14:48:31 | [maml_trainer] epoch #200 | Sampling for adapation and meta-testing... +2025-04-07 14:52:41 | [maml_trainer] epoch #200 | Finished meta-testing... +2025-04-07 14:52:41 | [maml_trainer] epoch #200 | Saving snapshot... +2025-04-07 14:53:04 | [maml_trainer] epoch #200 | Saved +2025-04-07 14:53:04 | [maml_trainer] epoch #200 | Time 339228.15 s +2025-04-07 14:53:04 | [maml_trainer] epoch #200 | EpochTime 1702.63 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.7733 +Average/AverageReturn -51.7313 +Average/Iteration 200 +Average/MaxReturn -43.9309 +Average/MinReturn -78.585 +Average/NumEpisodes 120 +Average/StdReturn 5.77722 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84221 +GaussianMLPPolicy/KLAfter 0.00325249 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.75635e-05 +GaussianMLPPolicy/LossBefore 9.02017e-09 +GaussianMLPPolicy/dLoss -5.75545e-05 +Iteration 200 +MetaTest/Average/AverageDiscountedReturn -50.0916 +MetaTest/Average/AverageReturn -50.0916 +MetaTest/Average/Iteration 200 +MetaTest/Average/MaxReturn -43.6046 +MetaTest/Average/MinReturn -58.5125 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.38803 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0916 +MetaTest/__unnamed_task__/AverageReturn -50.0916 +MetaTest/__unnamed_task__/Iteration 200 +MetaTest/__unnamed_task__/MaxReturn -43.6046 +MetaTest/__unnamed_task__/MinReturn -58.5125 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.38803 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.648e+06 +__unnamed_task__/AverageDiscountedReturn -28.7733 +__unnamed_task__/AverageReturn -51.7313 +__unnamed_task__/Iteration 200 +__unnamed_task__/MaxReturn -43.9309 +__unnamed_task__/MinReturn -78.585 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.77722 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 15:18:12 | [maml_trainer] epoch #201 | Sampling for adapation and meta-testing... +2025-04-07 15:22:27 | [maml_trainer] epoch #201 | Finished meta-testing... +2025-04-07 15:22:27 | [maml_trainer] epoch #201 | Saving snapshot... +2025-04-07 15:22:49 | [maml_trainer] epoch #201 | Saved +2025-04-07 15:22:49 | [maml_trainer] epoch #201 | Time 341013.83 s +2025-04-07 15:22:49 | [maml_trainer] epoch #201 | EpochTime 1785.67 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4034 +Average/AverageReturn -50.5016 +Average/Iteration 201 +Average/MaxReturn -39.8666 +Average/MinReturn -73.9659 +Average/NumEpisodes 120 +Average/StdReturn 5.64538 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84258 +GaussianMLPPolicy/KLAfter 0.00603439 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.19229e-05 +GaussianMLPPolicy/LossBefore 1.00136e-08 +GaussianMLPPolicy/dLoss -8.19129e-05 +Iteration 201 +MetaTest/Average/AverageDiscountedReturn -52.5593 +MetaTest/Average/AverageReturn -52.5593 +MetaTest/Average/Iteration 201 +MetaTest/Average/MaxReturn -43.049 +MetaTest/Average/MinReturn -98.379 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.8629 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.5593 +MetaTest/__unnamed_task__/AverageReturn -52.5593 +MetaTest/__unnamed_task__/Iteration 201 +MetaTest/__unnamed_task__/MaxReturn -43.049 +MetaTest/__unnamed_task__/MinReturn -98.379 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.8629 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.696e+06 +__unnamed_task__/AverageDiscountedReturn -28.4034 +__unnamed_task__/AverageReturn -50.5016 +__unnamed_task__/Iteration 201 +__unnamed_task__/MaxReturn -39.8666 +__unnamed_task__/MinReturn -73.9659 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.64538 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-07 15:47:38 | [maml_trainer] epoch #202 | Sampling for adapation and meta-testing... +2025-04-07 15:51:40 | [maml_trainer] epoch #202 | Finished meta-testing... +2025-04-07 15:51:40 | [maml_trainer] epoch #202 | Saving snapshot... +2025-04-07 15:52:01 | [maml_trainer] epoch #202 | Saved +2025-04-07 15:52:01 | [maml_trainer] epoch #202 | Time 342765.00 s +2025-04-07 15:52:01 | [maml_trainer] epoch #202 | EpochTime 1751.17 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.5901 +Average/AverageReturn -50.4816 +Average/Iteration 202 +Average/MaxReturn -40.679 +Average/MinReturn -73.326 +Average/NumEpisodes 120 +Average/StdReturn 5.8776 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84311 +GaussianMLPPolicy/KLAfter 0.0069974 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.0756e-05 +GaussianMLPPolicy/LossBefore -7.39098e-09 +GaussianMLPPolicy/dLoss -9.07634e-05 +Iteration 202 +MetaTest/Average/AverageDiscountedReturn -54.4466 +MetaTest/Average/AverageReturn -54.4466 +MetaTest/Average/Iteration 202 +MetaTest/Average/MaxReturn -41.6056 +MetaTest/Average/MinReturn -149.778 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 22.5056 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4466 +MetaTest/__unnamed_task__/AverageReturn -54.4466 +MetaTest/__unnamed_task__/Iteration 202 +MetaTest/__unnamed_task__/MaxReturn -41.6056 +MetaTest/__unnamed_task__/MinReturn -149.778 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 22.5056 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.744e+06 +__unnamed_task__/AverageDiscountedReturn -28.5901 +__unnamed_task__/AverageReturn -50.4816 +__unnamed_task__/Iteration 202 +__unnamed_task__/MaxReturn -40.679 +__unnamed_task__/MinReturn -73.326 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.8776 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 16:16:00 | [maml_trainer] epoch #203 | Sampling for adapation and meta-testing... +2025-04-07 16:20:07 | [maml_trainer] epoch #203 | Finished meta-testing... +2025-04-07 16:20:07 | [maml_trainer] epoch #203 | Saving snapshot... +2025-04-07 16:20:31 | [maml_trainer] epoch #203 | Saved +2025-04-07 16:20:31 | [maml_trainer] epoch #203 | Time 344475.11 s +2025-04-07 16:20:31 | [maml_trainer] epoch #203 | EpochTime 1710.11 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.7345 +Average/AverageReturn -52.3534 +Average/Iteration 203 +Average/MaxReturn -40.2094 +Average/MinReturn -104.987 +Average/NumEpisodes 120 +Average/StdReturn 11.8147 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84418 +GaussianMLPPolicy/KLAfter 0.00638604 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.77153e-05 +GaussianMLPPolicy/LossBefore -1.98682e-10 +GaussianMLPPolicy/dLoss -9.77155e-05 +Iteration 203 +MetaTest/Average/AverageDiscountedReturn -56.632 +MetaTest/Average/AverageReturn -56.632 +MetaTest/Average/Iteration 203 +MetaTest/Average/MaxReturn -44.9284 +MetaTest/Average/MinReturn -105.314 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 15.0431 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.632 +MetaTest/__unnamed_task__/AverageReturn -56.632 +MetaTest/__unnamed_task__/Iteration 203 +MetaTest/__unnamed_task__/MaxReturn -44.9284 +MetaTest/__unnamed_task__/MinReturn -105.314 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 15.0431 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.792e+06 +__unnamed_task__/AverageDiscountedReturn -28.7345 +__unnamed_task__/AverageReturn -52.3534 +__unnamed_task__/Iteration 203 +__unnamed_task__/MaxReturn -40.2094 +__unnamed_task__/MinReturn -104.987 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.8147 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 16:45:23 | [maml_trainer] epoch #204 | Sampling for adapation and meta-testing... +2025-04-07 16:49:31 | [maml_trainer] epoch #204 | Finished meta-testing... +2025-04-07 16:49:31 | [maml_trainer] epoch #204 | Saving snapshot... +2025-04-07 16:49:53 | [maml_trainer] epoch #204 | Saved +2025-04-07 16:49:53 | [maml_trainer] epoch #204 | Time 346237.71 s +2025-04-07 16:49:53 | [maml_trainer] epoch #204 | EpochTime 1762.59 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9258 +Average/AverageReturn -53.8705 +Average/Iteration 204 +Average/MaxReturn -34.9389 +Average/MinReturn -153.081 +Average/NumEpisodes 120 +Average/StdReturn 18.6297 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84431 +GaussianMLPPolicy/KLAfter 0.00464661 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000104802 +GaussianMLPPolicy/LossBefore 3.23852e-09 +GaussianMLPPolicy/dLoss -0.000104799 +Iteration 204 +MetaTest/Average/AverageDiscountedReturn -58.3702 +MetaTest/Average/AverageReturn -58.3702 +MetaTest/Average/Iteration 204 +MetaTest/Average/MaxReturn -43.312 +MetaTest/Average/MinReturn -147.969 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 23.1452 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.3702 +MetaTest/__unnamed_task__/AverageReturn -58.3702 +MetaTest/__unnamed_task__/Iteration 204 +MetaTest/__unnamed_task__/MaxReturn -43.312 +MetaTest/__unnamed_task__/MinReturn -147.969 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 23.1452 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.84e+06 +__unnamed_task__/AverageDiscountedReturn -28.9258 +__unnamed_task__/AverageReturn -53.8705 +__unnamed_task__/Iteration 204 +__unnamed_task__/MaxReturn -34.9389 +__unnamed_task__/MinReturn -153.081 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 18.6297 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 17:14:38 | [maml_trainer] epoch #205 | Sampling for adapation and meta-testing... +2025-04-07 17:18:43 | [maml_trainer] epoch #205 | Finished meta-testing... +2025-04-07 17:18:43 | [maml_trainer] epoch #205 | Saving snapshot... +2025-04-07 17:19:06 | [maml_trainer] epoch #205 | Saved +2025-04-07 17:19:06 | [maml_trainer] epoch #205 | Time 347990.30 s +2025-04-07 17:19:06 | [maml_trainer] epoch #205 | EpochTime 1752.58 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.7543 +Average/AverageReturn -63.1041 +Average/Iteration 205 +Average/MaxReturn 12.5963 +Average/MinReturn -175.178 +Average/NumEpisodes 120 +Average/StdReturn 30.0155 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84501 +GaussianMLPPolicy/KLAfter 0.00437147 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.40709e-06 +GaussianMLPPolicy/LossBefore -4.40081e-09 +GaussianMLPPolicy/dLoss -9.41149e-06 +Iteration 205 +MetaTest/Average/AverageDiscountedReturn -64.8932 +MetaTest/Average/AverageReturn -64.8932 +MetaTest/Average/Iteration 205 +MetaTest/Average/MaxReturn -31.3497 +MetaTest/Average/MinReturn -143.977 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 28.2172 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -64.8932 +MetaTest/__unnamed_task__/AverageReturn -64.8932 +MetaTest/__unnamed_task__/Iteration 205 +MetaTest/__unnamed_task__/MaxReturn -31.3497 +MetaTest/__unnamed_task__/MinReturn -143.977 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 28.2172 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.888e+06 +__unnamed_task__/AverageDiscountedReturn -30.7543 +__unnamed_task__/AverageReturn -63.1041 +__unnamed_task__/Iteration 205 +__unnamed_task__/MaxReturn 12.5963 +__unnamed_task__/MinReturn -175.178 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 30.0155 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 17:43:21 | [maml_trainer] epoch #206 | Sampling for adapation and meta-testing... +2025-04-07 17:47:29 | [maml_trainer] epoch #206 | Finished meta-testing... +2025-04-07 17:47:29 | [maml_trainer] epoch #206 | Saving snapshot... +2025-04-07 17:47:52 | [maml_trainer] epoch #206 | Saved +2025-04-07 17:47:52 | [maml_trainer] epoch #206 | Time 349715.98 s +2025-04-07 17:47:52 | [maml_trainer] epoch #206 | EpochTime 1725.68 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.9171 +Average/AverageReturn -62.1634 +Average/Iteration 206 +Average/MaxReturn 84.0455 +Average/MinReturn -174.2 +Average/NumEpisodes 120 +Average/StdReturn 33.5225 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84563 +GaussianMLPPolicy/KLAfter 0.00341457 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.08045e-05 +GaussianMLPPolicy/LossBefore -1.50998e-09 +GaussianMLPPolicy/dLoss 2.0803e-05 +Iteration 206 +MetaTest/Average/AverageDiscountedReturn -57.8641 +MetaTest/Average/AverageReturn -57.8641 +MetaTest/Average/Iteration 206 +MetaTest/Average/MaxReturn 371.518 +MetaTest/Average/MinReturn -180.633 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 107.68 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.8641 +MetaTest/__unnamed_task__/AverageReturn -57.8641 +MetaTest/__unnamed_task__/Iteration 206 +MetaTest/__unnamed_task__/MaxReturn 371.518 +MetaTest/__unnamed_task__/MinReturn -180.633 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 107.68 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.936e+06 +__unnamed_task__/AverageDiscountedReturn -30.9171 +__unnamed_task__/AverageReturn -62.1634 +__unnamed_task__/Iteration 206 +__unnamed_task__/MaxReturn 84.0455 +__unnamed_task__/MinReturn -174.2 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 33.5225 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 18:12:50 | [maml_trainer] epoch #207 | Sampling for adapation and meta-testing... +2025-04-07 18:16:56 | [maml_trainer] epoch #207 | Finished meta-testing... +2025-04-07 18:16:56 | [maml_trainer] epoch #207 | Saving snapshot... +2025-04-07 18:17:18 | [maml_trainer] epoch #207 | Saved +2025-04-07 18:17:18 | [maml_trainer] epoch #207 | Time 351482.72 s +2025-04-07 18:17:18 | [maml_trainer] epoch #207 | EpochTime 1766.74 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.3912 +Average/AverageReturn -60.2943 +Average/Iteration 207 +Average/MaxReturn 232.215 +Average/MinReturn -175.85 +Average/NumEpisodes 120 +Average/StdReturn 42.0688 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84591 +GaussianMLPPolicy/KLAfter 0.00239983 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.36323e-05 +GaussianMLPPolicy/LossBefore -1.66893e-09 +GaussianMLPPolicy/dLoss -2.3634e-05 +Iteration 207 +MetaTest/Average/AverageDiscountedReturn -64.8905 +MetaTest/Average/AverageReturn -64.8905 +MetaTest/Average/Iteration 207 +MetaTest/Average/MaxReturn 119.631 +MetaTest/Average/MinReturn -159.838 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 56.5676 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -64.8905 +MetaTest/__unnamed_task__/AverageReturn -64.8905 +MetaTest/__unnamed_task__/Iteration 207 +MetaTest/__unnamed_task__/MaxReturn 119.631 +MetaTest/__unnamed_task__/MinReturn -159.838 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 56.5676 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 9.984e+06 +__unnamed_task__/AverageDiscountedReturn -30.3912 +__unnamed_task__/AverageReturn -60.2943 +__unnamed_task__/Iteration 207 +__unnamed_task__/MaxReturn 232.215 +__unnamed_task__/MinReturn -175.85 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 42.0688 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 18:41:49 | [maml_trainer] epoch #208 | Sampling for adapation and meta-testing... +2025-04-07 18:45:53 | [maml_trainer] epoch #208 | Finished meta-testing... +2025-04-07 18:45:53 | [maml_trainer] epoch #208 | Saving snapshot... +2025-04-07 18:46:17 | [maml_trainer] epoch #208 | Saved +2025-04-07 18:46:17 | [maml_trainer] epoch #208 | Time 353221.65 s +2025-04-07 18:46:17 | [maml_trainer] epoch #208 | EpochTime 1738.93 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.4553 +Average/AverageReturn -68.4601 +Average/Iteration 208 +Average/MaxReturn 215.376 +Average/MinReturn -180.868 +Average/NumEpisodes 120 +Average/StdReturn 44.6869 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84563 +GaussianMLPPolicy/KLAfter 0.00163253 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.16279e-06 +GaussianMLPPolicy/LossBefore -7.35124e-10 +GaussianMLPPolicy/dLoss 3.16206e-06 +Iteration 208 +MetaTest/Average/AverageDiscountedReturn -58.0191 +MetaTest/Average/AverageReturn -58.0191 +MetaTest/Average/Iteration 208 +MetaTest/Average/MaxReturn -41.3967 +MetaTest/Average/MinReturn -106.859 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.8699 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.0191 +MetaTest/__unnamed_task__/AverageReturn -58.0191 +MetaTest/__unnamed_task__/Iteration 208 +MetaTest/__unnamed_task__/MaxReturn -41.3967 +MetaTest/__unnamed_task__/MinReturn -106.859 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.8699 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0032e+07 +__unnamed_task__/AverageDiscountedReturn -31.4553 +__unnamed_task__/AverageReturn -68.4601 +__unnamed_task__/Iteration 208 +__unnamed_task__/MaxReturn 215.376 +__unnamed_task__/MinReturn -180.868 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 44.6869 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 19:10:24 | [maml_trainer] epoch #209 | Sampling for adapation and meta-testing... +2025-04-07 19:14:39 | [maml_trainer] epoch #209 | Finished meta-testing... +2025-04-07 19:14:39 | [maml_trainer] epoch #209 | Saving snapshot... +2025-04-07 19:15:02 | [maml_trainer] epoch #209 | Saved +2025-04-07 19:15:02 | [maml_trainer] epoch #209 | Time 354946.68 s +2025-04-07 19:15:02 | [maml_trainer] epoch #209 | EpochTime 1725.02 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.8208 +Average/AverageReturn -74.7122 +Average/Iteration 209 +Average/MaxReturn 218.915 +Average/MinReturn -173.699 +Average/NumEpisodes 120 +Average/StdReturn 47.2449 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84543 +GaussianMLPPolicy/KLAfter 0.0012949 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.73223e-05 +GaussianMLPPolicy/LossBefore -4.56969e-10 +GaussianMLPPolicy/dLoss -1.73227e-05 +Iteration 209 +MetaTest/Average/AverageDiscountedReturn -74.381 +MetaTest/Average/AverageReturn -74.381 +MetaTest/Average/Iteration 209 +MetaTest/Average/MaxReturn -42.6604 +MetaTest/Average/MinReturn -162.096 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 33.7873 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -74.381 +MetaTest/__unnamed_task__/AverageReturn -74.381 +MetaTest/__unnamed_task__/Iteration 209 +MetaTest/__unnamed_task__/MaxReturn -42.6604 +MetaTest/__unnamed_task__/MinReturn -162.096 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 33.7873 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.008e+07 +__unnamed_task__/AverageDiscountedReturn -32.8208 +__unnamed_task__/AverageReturn -74.7122 +__unnamed_task__/Iteration 209 +__unnamed_task__/MaxReturn 218.915 +__unnamed_task__/MinReturn -173.699 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 47.2449 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 19:39:38 | [maml_trainer] epoch #210 | Sampling for adapation and meta-testing... +2025-04-07 19:43:42 | [maml_trainer] epoch #210 | Finished meta-testing... +2025-04-07 19:43:42 | [maml_trainer] epoch #210 | Saving snapshot... +2025-04-07 19:44:05 | [maml_trainer] epoch #210 | Saved +2025-04-07 19:44:05 | [maml_trainer] epoch #210 | Time 356689.80 s +2025-04-07 19:44:05 | [maml_trainer] epoch #210 | EpochTime 1743.12 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.3886 +Average/AverageReturn -70.5966 +Average/Iteration 210 +Average/MaxReturn 223.232 +Average/MinReturn -182.51 +Average/NumEpisodes 120 +Average/StdReturn 53.543 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84523 +GaussianMLPPolicy/KLAfter 0.00105162 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.83337e-06 +GaussianMLPPolicy/LossBefore 4.91738e-10 +GaussianMLPPolicy/dLoss 6.83387e-06 +Iteration 210 +MetaTest/Average/AverageDiscountedReturn -67.1593 +MetaTest/Average/AverageReturn -67.1593 +MetaTest/Average/Iteration 210 +MetaTest/Average/MaxReturn -32.9171 +MetaTest/Average/MinReturn -178.309 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 37.7217 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -67.1593 +MetaTest/__unnamed_task__/AverageReturn -67.1593 +MetaTest/__unnamed_task__/Iteration 210 +MetaTest/__unnamed_task__/MaxReturn -32.9171 +MetaTest/__unnamed_task__/MinReturn -178.309 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 37.7217 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0128e+07 +__unnamed_task__/AverageDiscountedReturn -32.3886 +__unnamed_task__/AverageReturn -70.5966 +__unnamed_task__/Iteration 210 +__unnamed_task__/MaxReturn 223.232 +__unnamed_task__/MinReturn -182.51 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 53.543 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 20:08:30 | [maml_trainer] epoch #211 | Sampling for adapation and meta-testing... +2025-04-07 20:12:33 | [maml_trainer] epoch #211 | Finished meta-testing... +2025-04-07 20:12:33 | [maml_trainer] epoch #211 | Saving snapshot... +2025-04-07 20:12:56 | [maml_trainer] epoch #211 | Saved +2025-04-07 20:12:56 | [maml_trainer] epoch #211 | Time 358420.47 s +2025-04-07 20:12:56 | [maml_trainer] epoch #211 | EpochTime 1730.67 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.7375 +Average/AverageReturn -78.9459 +Average/Iteration 211 +Average/MaxReturn 173.776 +Average/MinReturn -180.041 +Average/NumEpisodes 120 +Average/StdReturn 50.1509 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84491 +GaussianMLPPolicy/KLAfter 0.0010367 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.41262e-05 +GaussianMLPPolicy/LossBefore -1.45038e-09 +GaussianMLPPolicy/dLoss -1.41277e-05 +Iteration 211 +MetaTest/Average/AverageDiscountedReturn -91.1597 +MetaTest/Average/AverageReturn -91.1597 +MetaTest/Average/Iteration 211 +MetaTest/Average/MaxReturn 66.2809 +MetaTest/Average/MinReturn -170.223 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 55.9736 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -91.1597 +MetaTest/__unnamed_task__/AverageReturn -91.1597 +MetaTest/__unnamed_task__/Iteration 211 +MetaTest/__unnamed_task__/MaxReturn 66.2809 +MetaTest/__unnamed_task__/MinReturn -170.223 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 55.9736 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0176e+07 +__unnamed_task__/AverageDiscountedReturn -33.7375 +__unnamed_task__/AverageReturn -78.9459 +__unnamed_task__/Iteration 211 +__unnamed_task__/MaxReturn 173.776 +__unnamed_task__/MinReturn -180.041 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 50.1509 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 20:36:07 | [maml_trainer] epoch #212 | Sampling for adapation and meta-testing... +2025-04-07 20:39:56 | [maml_trainer] epoch #212 | Finished meta-testing... +2025-04-07 20:39:56 | [maml_trainer] epoch #212 | Saving snapshot... +2025-04-07 20:40:17 | [maml_trainer] epoch #212 | Saved +2025-04-07 20:40:17 | [maml_trainer] epoch #212 | Time 360061.93 s +2025-04-07 20:40:17 | [maml_trainer] epoch #212 | EpochTime 1641.45 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.8363 +Average/AverageReturn -85.3861 +Average/Iteration 212 +Average/MaxReturn 122.283 +Average/MinReturn -180.755 +Average/NumEpisodes 120 +Average/StdReturn 50.4011 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84461 +GaussianMLPPolicy/KLAfter 0.00124222 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.28514e-08 +GaussianMLPPolicy/LossBefore 4.78327e-09 +GaussianMLPPolicy/dLoss -6.80682e-08 +Iteration 212 +MetaTest/Average/AverageDiscountedReturn -97.9295 +MetaTest/Average/AverageReturn -97.9295 +MetaTest/Average/Iteration 212 +MetaTest/Average/MaxReturn 149.776 +MetaTest/Average/MinReturn -179.291 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 73.8397 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -97.9295 +MetaTest/__unnamed_task__/AverageReturn -97.9295 +MetaTest/__unnamed_task__/Iteration 212 +MetaTest/__unnamed_task__/MaxReturn 149.776 +MetaTest/__unnamed_task__/MinReturn -179.291 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 73.8397 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0224e+07 +__unnamed_task__/AverageDiscountedReturn -34.8363 +__unnamed_task__/AverageReturn -85.3861 +__unnamed_task__/Iteration 212 +__unnamed_task__/MaxReturn 122.283 +__unnamed_task__/MinReturn -180.755 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 50.4011 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 21:03:15 | [maml_trainer] epoch #213 | Sampling for adapation and meta-testing... +2025-04-07 21:07:13 | [maml_trainer] epoch #213 | Finished meta-testing... +2025-04-07 21:07:13 | [maml_trainer] epoch #213 | Saving snapshot... +2025-04-07 21:07:36 | [maml_trainer] epoch #213 | Saved +2025-04-07 21:07:36 | [maml_trainer] epoch #213 | Time 361699.97 s +2025-04-07 21:07:36 | [maml_trainer] epoch #213 | EpochTime 1638.03 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.3081 +Average/AverageReturn -75.0408 +Average/Iteration 213 +Average/MaxReturn 569.6 +Average/MinReturn -181.438 +Average/NumEpisodes 120 +Average/StdReturn 87.6944 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84459 +GaussianMLPPolicy/KLAfter 0.000831107 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.176e-05 +GaussianMLPPolicy/LossBefore 6.33299e-10 +GaussianMLPPolicy/dLoss -1.17594e-05 +Iteration 213 +MetaTest/Average/AverageDiscountedReturn -43.0997 +MetaTest/Average/AverageReturn -43.0997 +MetaTest/Average/Iteration 213 +MetaTest/Average/MaxReturn 452.598 +MetaTest/Average/MinReturn -149.423 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 117.463 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -43.0997 +MetaTest/__unnamed_task__/AverageReturn -43.0997 +MetaTest/__unnamed_task__/Iteration 213 +MetaTest/__unnamed_task__/MaxReturn 452.598 +MetaTest/__unnamed_task__/MinReturn -149.423 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 117.463 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0272e+07 +__unnamed_task__/AverageDiscountedReturn -33.3081 +__unnamed_task__/AverageReturn -75.0408 +__unnamed_task__/Iteration 213 +__unnamed_task__/MaxReturn 569.6 +__unnamed_task__/MinReturn -181.438 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 87.6944 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 21:31:54 | [maml_trainer] epoch #214 | Sampling for adapation and meta-testing... +2025-04-07 21:35:55 | [maml_trainer] epoch #214 | Finished meta-testing... +2025-04-07 21:35:55 | [maml_trainer] epoch #214 | Saving snapshot... +2025-04-07 21:36:18 | [maml_trainer] epoch #214 | Saved +2025-04-07 21:36:18 | [maml_trainer] epoch #214 | Time 363422.13 s +2025-04-07 21:36:18 | [maml_trainer] epoch #214 | EpochTime 1722.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.3772 +Average/AverageReturn -81.2388 +Average/Iteration 214 +Average/MaxReturn -4.30994 +Average/MinReturn -191.39 +Average/NumEpisodes 120 +Average/StdReturn 43.875 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84482 +GaussianMLPPolicy/KLAfter 0.000731566 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.16916e-07 +GaussianMLPPolicy/LossBefore 1.00831e-09 +GaussianMLPPolicy/dLoss 2.17925e-07 +Iteration 214 +MetaTest/Average/AverageDiscountedReturn -60.453 +MetaTest/Average/AverageReturn -60.453 +MetaTest/Average/Iteration 214 +MetaTest/Average/MaxReturn 153.183 +MetaTest/Average/MinReturn -166.283 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 58.5578 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -60.453 +MetaTest/__unnamed_task__/AverageReturn -60.453 +MetaTest/__unnamed_task__/Iteration 214 +MetaTest/__unnamed_task__/MaxReturn 153.183 +MetaTest/__unnamed_task__/MinReturn -166.283 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 58.5578 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.032e+07 +__unnamed_task__/AverageDiscountedReturn -34.3772 +__unnamed_task__/AverageReturn -81.2388 +__unnamed_task__/Iteration 214 +__unnamed_task__/MaxReturn -4.30994 +__unnamed_task__/MinReturn -191.39 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 43.875 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 22:00:27 | [maml_trainer] epoch #215 | Sampling for adapation and meta-testing... +2025-04-07 22:04:32 | [maml_trainer] epoch #215 | Finished meta-testing... +2025-04-07 22:04:32 | [maml_trainer] epoch #215 | Saving snapshot... +2025-04-07 22:04:54 | [maml_trainer] epoch #215 | Saved +2025-04-07 22:04:54 | [maml_trainer] epoch #215 | Time 365138.90 s +2025-04-07 22:04:54 | [maml_trainer] epoch #215 | EpochTime 1716.76 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -34.6551 +Average/AverageReturn -81.4791 +Average/Iteration 215 +Average/MaxReturn 37.8585 +Average/MinReturn -184.33 +Average/NumEpisodes 120 +Average/StdReturn 48.1979 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84481 +GaussianMLPPolicy/KLAfter 0.000498075 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.27544e-07 +GaussianMLPPolicy/LossBefore -1.04308e-10 +GaussianMLPPolicy/dLoss -4.27648e-07 +Iteration 215 +MetaTest/Average/AverageDiscountedReturn -93.6792 +MetaTest/Average/AverageReturn -93.6792 +MetaTest/Average/Iteration 215 +MetaTest/Average/MaxReturn -24.6998 +MetaTest/Average/MinReturn -180.452 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 53.3053 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -93.6792 +MetaTest/__unnamed_task__/AverageReturn -93.6792 +MetaTest/__unnamed_task__/Iteration 215 +MetaTest/__unnamed_task__/MaxReturn -24.6998 +MetaTest/__unnamed_task__/MinReturn -180.452 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 53.3053 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0368e+07 +__unnamed_task__/AverageDiscountedReturn -34.6551 +__unnamed_task__/AverageReturn -81.4791 +__unnamed_task__/Iteration 215 +__unnamed_task__/MaxReturn 37.8585 +__unnamed_task__/MinReturn -184.33 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 48.1979 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 22:29:15 | [maml_trainer] epoch #216 | Sampling for adapation and meta-testing... +2025-04-07 22:33:20 | [maml_trainer] epoch #216 | Finished meta-testing... +2025-04-07 22:33:20 | [maml_trainer] epoch #216 | Saving snapshot... +2025-04-07 22:33:42 | [maml_trainer] epoch #216 | Saved +2025-04-07 22:33:42 | [maml_trainer] epoch #216 | Time 366866.72 s +2025-04-07 22:33:42 | [maml_trainer] epoch #216 | EpochTime 1727.82 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.5424 +Average/AverageReturn -67.1759 +Average/Iteration 216 +Average/MaxReturn 291.717 +Average/MinReturn -181.919 +Average/NumEpisodes 120 +Average/StdReturn 55.9835 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84498 +GaussianMLPPolicy/KLAfter 0.000365958 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.29539e-06 +GaussianMLPPolicy/LossBefore 1.81546e-09 +GaussianMLPPolicy/dLoss 3.29721e-06 +Iteration 216 +MetaTest/Average/AverageDiscountedReturn -88.5721 +MetaTest/Average/AverageReturn -88.5721 +MetaTest/Average/Iteration 216 +MetaTest/Average/MaxReturn -44.0768 +MetaTest/Average/MinReturn -174.636 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 48.4091 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -88.5721 +MetaTest/__unnamed_task__/AverageReturn -88.5721 +MetaTest/__unnamed_task__/Iteration 216 +MetaTest/__unnamed_task__/MaxReturn -44.0768 +MetaTest/__unnamed_task__/MinReturn -174.636 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 48.4091 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0416e+07 +__unnamed_task__/AverageDiscountedReturn -32.5424 +__unnamed_task__/AverageReturn -67.1759 +__unnamed_task__/Iteration 216 +__unnamed_task__/MaxReturn 291.717 +__unnamed_task__/MinReturn -181.919 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 55.9835 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 22:57:53 | [maml_trainer] epoch #217 | Sampling for adapation and meta-testing... +2025-04-07 23:01:55 | [maml_trainer] epoch #217 | Finished meta-testing... +2025-04-07 23:01:55 | [maml_trainer] epoch #217 | Saving snapshot... +2025-04-07 23:02:18 | [maml_trainer] epoch #217 | Saved +2025-04-07 23:02:18 | [maml_trainer] epoch #217 | Time 368582.31 s +2025-04-07 23:02:18 | [maml_trainer] epoch #217 | EpochTime 1715.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.473 +Average/AverageReturn -67.2906 +Average/Iteration 217 +Average/MaxReturn 18.3245 +Average/MinReturn -184.548 +Average/NumEpisodes 120 +Average/StdReturn 37.518 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84508 +GaussianMLPPolicy/KLAfter 0.000567962 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.8983e-05 +GaussianMLPPolicy/LossBefore -2.6226e-09 +GaussianMLPPolicy/dLoss 2.89804e-05 +Iteration 217 +MetaTest/Average/AverageDiscountedReturn -67.767 +MetaTest/Average/AverageReturn -67.767 +MetaTest/Average/Iteration 217 +MetaTest/Average/MaxReturn -42.6176 +MetaTest/Average/MinReturn -173.924 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 36.6993 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -67.767 +MetaTest/__unnamed_task__/AverageReturn -67.767 +MetaTest/__unnamed_task__/Iteration 217 +MetaTest/__unnamed_task__/MaxReturn -42.6176 +MetaTest/__unnamed_task__/MinReturn -173.924 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 36.6993 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0464e+07 +__unnamed_task__/AverageDiscountedReturn -32.473 +__unnamed_task__/AverageReturn -67.2906 +__unnamed_task__/Iteration 217 +__unnamed_task__/MaxReturn 18.3245 +__unnamed_task__/MinReturn -184.548 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 37.518 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 23:26:15 | [maml_trainer] epoch #218 | Sampling for adapation and meta-testing... +2025-04-07 23:30:14 | [maml_trainer] epoch #218 | Finished meta-testing... +2025-04-07 23:30:14 | [maml_trainer] epoch #218 | Saving snapshot... +2025-04-07 23:30:36 | [maml_trainer] epoch #218 | Saved +2025-04-07 23:30:36 | [maml_trainer] epoch #218 | Time 370280.37 s +2025-04-07 23:30:36 | [maml_trainer] epoch #218 | EpochTime 1698.05 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -33.4158 +Average/AverageReturn -72.4132 +Average/Iteration 218 +Average/MaxReturn 145.952 +Average/MinReturn -179.46 +Average/NumEpisodes 120 +Average/StdReturn 42.7261 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84605 +GaussianMLPPolicy/KLAfter 0.000798306 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.48678e-05 +GaussianMLPPolicy/LossBefore -5.46376e-10 +GaussianMLPPolicy/dLoss 2.48673e-05 +Iteration 218 +MetaTest/Average/AverageDiscountedReturn -74.2311 +MetaTest/Average/AverageReturn -74.2311 +MetaTest/Average/Iteration 218 +MetaTest/Average/MaxReturn -44.8012 +MetaTest/Average/MinReturn -174.742 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 37.7341 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -74.2311 +MetaTest/__unnamed_task__/AverageReturn -74.2311 +MetaTest/__unnamed_task__/Iteration 218 +MetaTest/__unnamed_task__/MaxReturn -44.8012 +MetaTest/__unnamed_task__/MinReturn -174.742 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 37.7341 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0512e+07 +__unnamed_task__/AverageDiscountedReturn -33.4158 +__unnamed_task__/AverageReturn -72.4132 +__unnamed_task__/Iteration 218 +__unnamed_task__/MaxReturn 145.952 +__unnamed_task__/MinReturn -179.46 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 42.7261 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-07 23:54:47 | [maml_trainer] epoch #219 | Sampling for adapation and meta-testing... +2025-04-07 23:58:57 | [maml_trainer] epoch #219 | Finished meta-testing... +2025-04-07 23:58:57 | [maml_trainer] epoch #219 | Saving snapshot... +2025-04-07 23:59:19 | [maml_trainer] epoch #219 | Saved +2025-04-07 23:59:19 | [maml_trainer] epoch #219 | Time 372003.53 s +2025-04-07 23:59:19 | [maml_trainer] epoch #219 | EpochTime 1723.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -32.4852 +Average/AverageReturn -64.9872 +Average/Iteration 219 +Average/MaxReturn -44.8111 +Average/MinReturn -179.797 +Average/NumEpisodes 120 +Average/StdReturn 29.6405 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84658 +GaussianMLPPolicy/KLAfter 0.000834515 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.251e-05 +GaussianMLPPolicy/LossBefore -2.54313e-09 +GaussianMLPPolicy/dLoss 8.25074e-05 +Iteration 219 +MetaTest/Average/AverageDiscountedReturn -56.4674 +MetaTest/Average/AverageReturn -56.4674 +MetaTest/Average/Iteration 219 +MetaTest/Average/MaxReturn -42.8188 +MetaTest/Average/MinReturn -103.84 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.3131 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.4674 +MetaTest/__unnamed_task__/AverageReturn -56.4674 +MetaTest/__unnamed_task__/Iteration 219 +MetaTest/__unnamed_task__/MaxReturn -42.8188 +MetaTest/__unnamed_task__/MinReturn -103.84 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.3131 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.056e+07 +__unnamed_task__/AverageDiscountedReturn -32.4852 +__unnamed_task__/AverageReturn -64.9872 +__unnamed_task__/Iteration 219 +__unnamed_task__/MaxReturn -44.8111 +__unnamed_task__/MinReturn -179.797 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 29.6405 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 00:23:41 | [maml_trainer] epoch #220 | Sampling for adapation and meta-testing... +2025-04-08 00:27:46 | [maml_trainer] epoch #220 | Finished meta-testing... +2025-04-08 00:27:46 | [maml_trainer] epoch #220 | Saving snapshot... +2025-04-08 00:28:10 | [maml_trainer] epoch #220 | Saved +2025-04-08 00:28:10 | [maml_trainer] epoch #220 | Time 373734.03 s +2025-04-08 00:28:10 | [maml_trainer] epoch #220 | EpochTime 1730.50 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.7954 +Average/AverageReturn -61.0628 +Average/Iteration 220 +Average/MaxReturn -43.5615 +Average/MinReturn -186.096 +Average/NumEpisodes 120 +Average/StdReturn 25.5624 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84708 +GaussianMLPPolicy/KLAfter 0.00143132 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.23607e-05 +GaussianMLPPolicy/LossBefore -2.58287e-09 +GaussianMLPPolicy/dLoss 8.23582e-05 +Iteration 220 +MetaTest/Average/AverageDiscountedReturn -56.8087 +MetaTest/Average/AverageReturn -56.8087 +MetaTest/Average/Iteration 220 +MetaTest/Average/MaxReturn -43.2111 +MetaTest/Average/MinReturn -94.2869 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.3983 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.8087 +MetaTest/__unnamed_task__/AverageReturn -56.8087 +MetaTest/__unnamed_task__/Iteration 220 +MetaTest/__unnamed_task__/MaxReturn -43.2111 +MetaTest/__unnamed_task__/MinReturn -94.2869 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.3983 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0608e+07 +__unnamed_task__/AverageDiscountedReturn -31.7954 +__unnamed_task__/AverageReturn -61.0628 +__unnamed_task__/Iteration 220 +__unnamed_task__/MaxReturn -43.5615 +__unnamed_task__/MinReturn -186.096 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 25.5624 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 00:52:34 | [maml_trainer] epoch #221 | Sampling for adapation and meta-testing... +2025-04-08 00:56:36 | [maml_trainer] epoch #221 | Finished meta-testing... +2025-04-08 00:56:36 | [maml_trainer] epoch #221 | Saving snapshot... +2025-04-08 00:56:59 | [maml_trainer] epoch #221 | Saved +2025-04-08 00:56:59 | [maml_trainer] epoch #221 | Time 375463.57 s +2025-04-08 00:56:59 | [maml_trainer] epoch #221 | EpochTime 1729.53 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -31.43 +Average/AverageReturn -58.261 +Average/Iteration 221 +Average/MaxReturn -42.4764 +Average/MinReturn -155.169 +Average/NumEpisodes 120 +Average/StdReturn 17.357 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84713 +GaussianMLPPolicy/KLAfter 0.00170075 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.95687e-05 +GaussianMLPPolicy/LossBefore -3.57628e-09 +GaussianMLPPolicy/dLoss 6.95651e-05 +Iteration 221 +MetaTest/Average/AverageDiscountedReturn -52.8031 +MetaTest/Average/AverageReturn -52.8031 +MetaTest/Average/Iteration 221 +MetaTest/Average/MaxReturn -43.4718 +MetaTest/Average/MinReturn -72.3841 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.72631 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8031 +MetaTest/__unnamed_task__/AverageReturn -52.8031 +MetaTest/__unnamed_task__/Iteration 221 +MetaTest/__unnamed_task__/MaxReturn -43.4718 +MetaTest/__unnamed_task__/MinReturn -72.3841 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.72631 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0656e+07 +__unnamed_task__/AverageDiscountedReturn -31.43 +__unnamed_task__/AverageReturn -58.261 +__unnamed_task__/Iteration 221 +__unnamed_task__/MaxReturn -42.4764 +__unnamed_task__/MinReturn -155.169 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.357 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 01:20:47 | [maml_trainer] epoch #222 | Sampling for adapation and meta-testing... +2025-04-08 01:24:37 | [maml_trainer] epoch #222 | Finished meta-testing... +2025-04-08 01:24:37 | [maml_trainer] epoch #222 | Saving snapshot... +2025-04-08 01:24:59 | [maml_trainer] epoch #222 | Saved +2025-04-08 01:24:59 | [maml_trainer] epoch #222 | Time 377143.06 s +2025-04-08 01:24:59 | [maml_trainer] epoch #222 | EpochTime 1679.49 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -30.9878 +Average/AverageReturn -56.3621 +Average/Iteration 222 +Average/MaxReturn -41.8165 +Average/MinReturn -178.657 +Average/NumEpisodes 120 +Average/StdReturn 16.4418 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84735 +GaussianMLPPolicy/KLAfter 0.00153284 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.8072e-05 +GaussianMLPPolicy/LossBefore 6.39757e-09 +GaussianMLPPolicy/dLoss 4.80784e-05 +Iteration 222 +MetaTest/Average/AverageDiscountedReturn -53.6769 +MetaTest/Average/AverageReturn -53.6769 +MetaTest/Average/Iteration 222 +MetaTest/Average/MaxReturn -48.1442 +MetaTest/Average/MinReturn -70.0109 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.98105 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6769 +MetaTest/__unnamed_task__/AverageReturn -53.6769 +MetaTest/__unnamed_task__/Iteration 222 +MetaTest/__unnamed_task__/MaxReturn -48.1442 +MetaTest/__unnamed_task__/MinReturn -70.0109 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.98105 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0704e+07 +__unnamed_task__/AverageDiscountedReturn -30.9878 +__unnamed_task__/AverageReturn -56.3621 +__unnamed_task__/Iteration 222 +__unnamed_task__/MaxReturn -41.8165 +__unnamed_task__/MinReturn -178.657 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.4418 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 02:14:07 | [maml_trainer] epoch #223 | Sampling for adapation and meta-testing... +2025-04-08 02:17:56 | [maml_trainer] epoch #223 | Finished meta-testing... +2025-04-08 02:17:56 | [maml_trainer] epoch #223 | Saving snapshot... +2025-04-08 02:18:18 | [maml_trainer] epoch #223 | Saved +2025-04-08 02:18:18 | [maml_trainer] epoch #223 | Time 380342.31 s +2025-04-08 02:18:18 | [maml_trainer] epoch #223 | EpochTime 3199.24 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.8355 +Average/AverageReturn -54.4175 +Average/Iteration 223 +Average/MaxReturn -44.2098 +Average/MinReturn -78.9861 +Average/NumEpisodes 120 +Average/StdReturn 5.27974 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84747 +GaussianMLPPolicy/KLAfter 0.0020266 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.64764e-05 +GaussianMLPPolicy/LossBefore 7.11282e-09 +GaussianMLPPolicy/dLoss 4.64835e-05 +Iteration 223 +MetaTest/Average/AverageDiscountedReturn -54.1243 +MetaTest/Average/AverageReturn -54.1243 +MetaTest/Average/Iteration 223 +MetaTest/Average/MaxReturn -45.607 +MetaTest/Average/MinReturn -67.4636 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.31771 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1243 +MetaTest/__unnamed_task__/AverageReturn -54.1243 +MetaTest/__unnamed_task__/Iteration 223 +MetaTest/__unnamed_task__/MaxReturn -45.607 +MetaTest/__unnamed_task__/MinReturn -67.4636 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.31771 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0752e+07 +__unnamed_task__/AverageDiscountedReturn -30.8355 +__unnamed_task__/AverageReturn -54.4175 +__unnamed_task__/Iteration 223 +__unnamed_task__/MaxReturn -44.2098 +__unnamed_task__/MinReturn -78.9861 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.27974 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 02:41:23 | [maml_trainer] epoch #224 | Sampling for adapation and meta-testing... +2025-04-08 02:45:16 | [maml_trainer] epoch #224 | Finished meta-testing... +2025-04-08 02:45:16 | [maml_trainer] epoch #224 | Saving snapshot... +2025-04-08 02:45:38 | [maml_trainer] epoch #224 | Saved +2025-04-08 02:45:38 | [maml_trainer] epoch #224 | Time 381982.57 s +2025-04-08 02:45:38 | [maml_trainer] epoch #224 | EpochTime 1640.26 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.8542 +Average/AverageReturn -54.602 +Average/Iteration 224 +Average/MaxReturn -44.7515 +Average/MinReturn -67.2628 +Average/NumEpisodes 120 +Average/StdReturn 4.60167 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84811 +GaussianMLPPolicy/KLAfter 0.001775 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.17248e-05 +GaussianMLPPolicy/LossBefore 1.83185e-08 +GaussianMLPPolicy/dLoss 3.17432e-05 +Iteration 224 +MetaTest/Average/AverageDiscountedReturn -54.2125 +MetaTest/Average/AverageReturn -54.2125 +MetaTest/Average/Iteration 224 +MetaTest/Average/MaxReturn -45.9705 +MetaTest/Average/MinReturn -65.2442 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.88956 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.2125 +MetaTest/__unnamed_task__/AverageReturn -54.2125 +MetaTest/__unnamed_task__/Iteration 224 +MetaTest/__unnamed_task__/MaxReturn -45.9705 +MetaTest/__unnamed_task__/MinReturn -65.2442 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.88956 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.08e+07 +__unnamed_task__/AverageDiscountedReturn -30.8542 +__unnamed_task__/AverageReturn -54.602 +__unnamed_task__/Iteration 224 +__unnamed_task__/MaxReturn -44.7515 +__unnamed_task__/MinReturn -67.2628 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.60167 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 03:09:06 | [maml_trainer] epoch #225 | Sampling for adapation and meta-testing... +2025-04-08 03:12:57 | [maml_trainer] epoch #225 | Finished meta-testing... +2025-04-08 03:12:57 | [maml_trainer] epoch #225 | Saving snapshot... +2025-04-08 03:13:18 | [maml_trainer] epoch #225 | Saved +2025-04-08 03:13:18 | [maml_trainer] epoch #225 | Time 383642.32 s +2025-04-08 03:13:18 | [maml_trainer] epoch #225 | EpochTime 1659.75 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.4771 +Average/AverageReturn -54.116 +Average/Iteration 225 +Average/MaxReturn -43.3829 +Average/MinReturn -74.4891 +Average/NumEpisodes 120 +Average/StdReturn 5.38262 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84938 +GaussianMLPPolicy/KLAfter 0.00148067 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.39287e-05 +GaussianMLPPolicy/LossBefore 5.126e-09 +GaussianMLPPolicy/dLoss -4.39236e-05 +Iteration 225 +MetaTest/Average/AverageDiscountedReturn -52.2795 +MetaTest/Average/AverageReturn -52.2795 +MetaTest/Average/Iteration 225 +MetaTest/Average/MaxReturn -43.4853 +MetaTest/Average/MinReturn -62.5078 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.91932 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2795 +MetaTest/__unnamed_task__/AverageReturn -52.2795 +MetaTest/__unnamed_task__/Iteration 225 +MetaTest/__unnamed_task__/MaxReturn -43.4853 +MetaTest/__unnamed_task__/MinReturn -62.5078 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.91932 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0848e+07 +__unnamed_task__/AverageDiscountedReturn -30.4771 +__unnamed_task__/AverageReturn -54.116 +__unnamed_task__/Iteration 225 +__unnamed_task__/MaxReturn -43.3829 +__unnamed_task__/MinReturn -74.4891 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.38262 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 03:36:16 | [maml_trainer] epoch #226 | Sampling for adapation and meta-testing... +2025-04-08 03:40:05 | [maml_trainer] epoch #226 | Finished meta-testing... +2025-04-08 03:40:05 | [maml_trainer] epoch #226 | Saving snapshot... +2025-04-08 03:40:26 | [maml_trainer] epoch #226 | Saved +2025-04-08 03:40:26 | [maml_trainer] epoch #226 | Time 385270.56 s +2025-04-08 03:40:26 | [maml_trainer] epoch #226 | EpochTime 1628.23 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.5747 +Average/AverageReturn -54.1625 +Average/Iteration 226 +Average/MaxReturn -44.3123 +Average/MinReturn -67.5701 +Average/NumEpisodes 120 +Average/StdReturn 5.18402 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84932 +GaussianMLPPolicy/KLAfter 0.000547848 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.49244e-05 +GaussianMLPPolicy/LossBefore 1.20799e-08 +GaussianMLPPolicy/dLoss -4.49123e-05 +Iteration 226 +MetaTest/Average/AverageDiscountedReturn -53.8645 +MetaTest/Average/AverageReturn -53.8645 +MetaTest/Average/Iteration 226 +MetaTest/Average/MaxReturn -49.6632 +MetaTest/Average/MinReturn -61.2228 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.49717 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.8645 +MetaTest/__unnamed_task__/AverageReturn -53.8645 +MetaTest/__unnamed_task__/Iteration 226 +MetaTest/__unnamed_task__/MaxReturn -49.6632 +MetaTest/__unnamed_task__/MinReturn -61.2228 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.49717 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0896e+07 +__unnamed_task__/AverageDiscountedReturn -30.5747 +__unnamed_task__/AverageReturn -54.1625 +__unnamed_task__/Iteration 226 +__unnamed_task__/MaxReturn -44.3123 +__unnamed_task__/MinReturn -67.5701 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.18402 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 04:03:13 | [maml_trainer] epoch #227 | Sampling for adapation and meta-testing... +2025-04-08 04:07:05 | [maml_trainer] epoch #227 | Finished meta-testing... +2025-04-08 04:07:05 | [maml_trainer] epoch #227 | Saving snapshot... +2025-04-08 04:07:27 | [maml_trainer] epoch #227 | Saved +2025-04-08 04:07:27 | [maml_trainer] epoch #227 | Time 386891.42 s +2025-04-08 04:07:27 | [maml_trainer] epoch #227 | EpochTime 1620.86 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.5354 +Average/AverageReturn -54.4566 +Average/Iteration 227 +Average/MaxReturn -44.6645 +Average/MinReturn -71.6315 +Average/NumEpisodes 120 +Average/StdReturn 5.0443 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84819 +GaussianMLPPolicy/KLAfter 0.00102144 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.22712e-06 +GaussianMLPPolicy/LossBefore 6.39757e-09 +GaussianMLPPolicy/dLoss -4.22072e-06 +Iteration 227 +MetaTest/Average/AverageDiscountedReturn -52.3155 +MetaTest/Average/AverageReturn -52.3155 +MetaTest/Average/Iteration 227 +MetaTest/Average/MaxReturn -47.1095 +MetaTest/Average/MinReturn -58.8453 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.75793 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3155 +MetaTest/__unnamed_task__/AverageReturn -52.3155 +MetaTest/__unnamed_task__/Iteration 227 +MetaTest/__unnamed_task__/MaxReturn -47.1095 +MetaTest/__unnamed_task__/MinReturn -58.8453 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.75793 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0944e+07 +__unnamed_task__/AverageDiscountedReturn -30.5354 +__unnamed_task__/AverageReturn -54.4566 +__unnamed_task__/Iteration 227 +__unnamed_task__/MaxReturn -44.6645 +__unnamed_task__/MinReturn -71.6315 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.0443 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 04:30:26 | [maml_trainer] epoch #228 | Sampling for adapation and meta-testing... +2025-04-08 04:34:13 | [maml_trainer] epoch #228 | Finished meta-testing... +2025-04-08 04:34:13 | [maml_trainer] epoch #228 | Saving snapshot... +2025-04-08 04:34:34 | [maml_trainer] epoch #228 | Saved +2025-04-08 04:34:34 | [maml_trainer] epoch #228 | Time 388518.76 s +2025-04-08 04:34:34 | [maml_trainer] epoch #228 | EpochTime 1627.33 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.4646 +Average/AverageReturn -54.5988 +Average/Iteration 228 +Average/MaxReturn -45.3556 +Average/MinReturn -72.4068 +Average/NumEpisodes 120 +Average/StdReturn 5.49055 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84847 +GaussianMLPPolicy/KLAfter 0.000902898 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.65983e-05 +GaussianMLPPolicy/LossBefore -1.00931e-08 +GaussianMLPPolicy/dLoss -1.66084e-05 +Iteration 228 +MetaTest/Average/AverageDiscountedReturn -54.5802 +MetaTest/Average/AverageReturn -54.5802 +MetaTest/Average/Iteration 228 +MetaTest/Average/MaxReturn -47.191 +MetaTest/Average/MinReturn -72.0911 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.90902 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.5802 +MetaTest/__unnamed_task__/AverageReturn -54.5802 +MetaTest/__unnamed_task__/Iteration 228 +MetaTest/__unnamed_task__/MaxReturn -47.191 +MetaTest/__unnamed_task__/MinReturn -72.0911 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.90902 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.0992e+07 +__unnamed_task__/AverageDiscountedReturn -30.4646 +__unnamed_task__/AverageReturn -54.5988 +__unnamed_task__/Iteration 228 +__unnamed_task__/MaxReturn -45.3556 +__unnamed_task__/MinReturn -72.4068 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.49055 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 04:57:20 | [maml_trainer] epoch #229 | Sampling for adapation and meta-testing... +2025-04-08 05:01:13 | [maml_trainer] epoch #229 | Finished meta-testing... +2025-04-08 05:01:13 | [maml_trainer] epoch #229 | Saving snapshot... +2025-04-08 05:01:35 | [maml_trainer] epoch #229 | Saved +2025-04-08 05:01:35 | [maml_trainer] epoch #229 | Time 390139.26 s +2025-04-08 05:01:35 | [maml_trainer] epoch #229 | EpochTime 1620.50 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.9718 +Average/AverageReturn -53.353 +Average/Iteration 229 +Average/MaxReturn -43.8429 +Average/MinReturn -74.3876 +Average/NumEpisodes 120 +Average/StdReturn 5.39783 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84665 +GaussianMLPPolicy/KLAfter 0.00192779 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.16907e-06 +GaussianMLPPolicy/LossBefore 8.38439e-09 +GaussianMLPPolicy/dLoss 4.17745e-06 +Iteration 229 +MetaTest/Average/AverageDiscountedReturn -54.0312 +MetaTest/Average/AverageReturn -54.0312 +MetaTest/Average/Iteration 229 +MetaTest/Average/MaxReturn -46.9553 +MetaTest/Average/MinReturn -75.817 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.48531 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.0312 +MetaTest/__unnamed_task__/AverageReturn -54.0312 +MetaTest/__unnamed_task__/Iteration 229 +MetaTest/__unnamed_task__/MaxReturn -46.9553 +MetaTest/__unnamed_task__/MinReturn -75.817 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.48531 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.104e+07 +__unnamed_task__/AverageDiscountedReturn -29.9718 +__unnamed_task__/AverageReturn -53.353 +__unnamed_task__/Iteration 229 +__unnamed_task__/MaxReturn -43.8429 +__unnamed_task__/MinReturn -74.3876 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.39783 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 05:24:49 | [maml_trainer] epoch #230 | Sampling for adapation and meta-testing... +2025-04-08 05:28:41 | [maml_trainer] epoch #230 | Finished meta-testing... +2025-04-08 05:28:41 | [maml_trainer] epoch #230 | Saving snapshot... +2025-04-08 05:29:03 | [maml_trainer] epoch #230 | Saved +2025-04-08 05:29:03 | [maml_trainer] epoch #230 | Time 391787.19 s +2025-04-08 05:29:03 | [maml_trainer] epoch #230 | EpochTime 1647.92 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -30.0965 +Average/AverageReturn -53.4324 +Average/Iteration 230 +Average/MaxReturn -44.1763 +Average/MinReturn -70.0169 +Average/NumEpisodes 120 +Average/StdReturn 5.3604 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84393 +GaussianMLPPolicy/KLAfter 0.00178547 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.73275e-05 +GaussianMLPPolicy/LossBefore 4.29153e-09 +GaussianMLPPolicy/dLoss 1.73318e-05 +Iteration 230 +MetaTest/Average/AverageDiscountedReturn -51.0995 +MetaTest/Average/AverageReturn -51.0995 +MetaTest/Average/Iteration 230 +MetaTest/Average/MaxReturn -45.0423 +MetaTest/Average/MinReturn -63.549 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.26865 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.0995 +MetaTest/__unnamed_task__/AverageReturn -51.0995 +MetaTest/__unnamed_task__/Iteration 230 +MetaTest/__unnamed_task__/MaxReturn -45.0423 +MetaTest/__unnamed_task__/MinReturn -63.549 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.26865 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1088e+07 +__unnamed_task__/AverageDiscountedReturn -30.0965 +__unnamed_task__/AverageReturn -53.4324 +__unnamed_task__/Iteration 230 +__unnamed_task__/MaxReturn -44.1763 +__unnamed_task__/MinReturn -70.0169 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.3604 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 05:51:54 | [maml_trainer] epoch #231 | Sampling for adapation and meta-testing... +2025-04-08 05:55:46 | [maml_trainer] epoch #231 | Finished meta-testing... +2025-04-08 05:55:46 | [maml_trainer] epoch #231 | Saving snapshot... +2025-04-08 05:56:08 | [maml_trainer] epoch #231 | Saved +2025-04-08 05:56:08 | [maml_trainer] epoch #231 | Time 393411.98 s +2025-04-08 05:56:08 | [maml_trainer] epoch #231 | EpochTime 1624.79 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.8013 +Average/AverageReturn -52.6333 +Average/Iteration 231 +Average/MaxReturn -44.1102 +Average/MinReturn -64.6575 +Average/NumEpisodes 120 +Average/StdReturn 4.14468 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84149 +GaussianMLPPolicy/KLAfter 0.00245707 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.23451e-05 +GaussianMLPPolicy/LossBefore -5.126e-09 +GaussianMLPPolicy/dLoss -7.23502e-05 +Iteration 231 +MetaTest/Average/AverageDiscountedReturn -52.0377 +MetaTest/Average/AverageReturn -52.0377 +MetaTest/Average/Iteration 231 +MetaTest/Average/MaxReturn -45.8797 +MetaTest/Average/MinReturn -57.7637 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.8609 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.0377 +MetaTest/__unnamed_task__/AverageReturn -52.0377 +MetaTest/__unnamed_task__/Iteration 231 +MetaTest/__unnamed_task__/MaxReturn -45.8797 +MetaTest/__unnamed_task__/MinReturn -57.7637 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.8609 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1136e+07 +__unnamed_task__/AverageDiscountedReturn -29.8013 +__unnamed_task__/AverageReturn -52.6333 +__unnamed_task__/Iteration 231 +__unnamed_task__/MaxReturn -44.1102 +__unnamed_task__/MinReturn -64.6575 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.14468 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 06:19:14 | [maml_trainer] epoch #232 | Sampling for adapation and meta-testing... +2025-04-08 06:23:08 | [maml_trainer] epoch #232 | Finished meta-testing... +2025-04-08 06:23:08 | [maml_trainer] epoch #232 | Saving snapshot... +2025-04-08 06:23:30 | [maml_trainer] epoch #232 | Saved +2025-04-08 06:23:30 | [maml_trainer] epoch #232 | Time 395054.71 s +2025-04-08 06:23:30 | [maml_trainer] epoch #232 | EpochTime 1642.73 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.2189 +Average/AverageReturn -51.2649 +Average/Iteration 232 +Average/MaxReturn -42.1524 +Average/MinReturn -71.2547 +Average/NumEpisodes 120 +Average/StdReturn 4.42689 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83825 +GaussianMLPPolicy/KLAfter 0.00310522 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.39582e-05 +GaussianMLPPolicy/LossBefore -1.50998e-08 +GaussianMLPPolicy/dLoss 4.39431e-05 +Iteration 232 +MetaTest/Average/AverageDiscountedReturn -50.961 +MetaTest/Average/AverageReturn -50.961 +MetaTest/Average/Iteration 232 +MetaTest/Average/MaxReturn -45.5579 +MetaTest/Average/MinReturn -56.9673 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.25829 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.961 +MetaTest/__unnamed_task__/AverageReturn -50.961 +MetaTest/__unnamed_task__/Iteration 232 +MetaTest/__unnamed_task__/MaxReturn -45.5579 +MetaTest/__unnamed_task__/MinReturn -56.9673 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.25829 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1184e+07 +__unnamed_task__/AverageDiscountedReturn -29.2189 +__unnamed_task__/AverageReturn -51.2649 +__unnamed_task__/Iteration 232 +__unnamed_task__/MaxReturn -42.1524 +__unnamed_task__/MinReturn -71.2547 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.42689 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 06:47:02 | [maml_trainer] epoch #233 | Sampling for adapation and meta-testing... +2025-04-08 06:50:56 | [maml_trainer] epoch #233 | Finished meta-testing... +2025-04-08 06:50:56 | [maml_trainer] epoch #233 | Saving snapshot... +2025-04-08 06:51:18 | [maml_trainer] epoch #233 | Saved +2025-04-08 06:51:18 | [maml_trainer] epoch #233 | Time 396722.24 s +2025-04-08 06:51:18 | [maml_trainer] epoch #233 | EpochTime 1667.52 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.5677 +Average/AverageReturn -52.0624 +Average/Iteration 233 +Average/MaxReturn -44.7506 +Average/MinReturn -66.7195 +Average/NumEpisodes 120 +Average/StdReturn 4.4741 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83534 +GaussianMLPPolicy/KLAfter 0.00260178 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000113778 +GaussianMLPPolicy/LossBefore 8.98043e-09 +GaussianMLPPolicy/dLoss 0.000113787 +Iteration 233 +MetaTest/Average/AverageDiscountedReturn -50.3319 +MetaTest/Average/AverageReturn -50.3319 +MetaTest/Average/Iteration 233 +MetaTest/Average/MaxReturn -45.8276 +MetaTest/Average/MinReturn -53.5706 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.11325 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3319 +MetaTest/__unnamed_task__/AverageReturn -50.3319 +MetaTest/__unnamed_task__/Iteration 233 +MetaTest/__unnamed_task__/MaxReturn -45.8276 +MetaTest/__unnamed_task__/MinReturn -53.5706 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.11325 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1232e+07 +__unnamed_task__/AverageDiscountedReturn -29.5677 +__unnamed_task__/AverageReturn -52.0624 +__unnamed_task__/Iteration 233 +__unnamed_task__/MaxReturn -44.7506 +__unnamed_task__/MinReturn -66.7195 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.4741 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 07:14:25 | [maml_trainer] epoch #234 | Sampling for adapation and meta-testing... +2025-04-08 07:18:25 | [maml_trainer] epoch #234 | Finished meta-testing... +2025-04-08 07:18:25 | [maml_trainer] epoch #234 | Saving snapshot... +2025-04-08 07:18:47 | [maml_trainer] epoch #234 | Saved +2025-04-08 07:18:47 | [maml_trainer] epoch #234 | Time 398371.26 s +2025-04-08 07:18:47 | [maml_trainer] epoch #234 | EpochTime 1649.02 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.0446 +Average/AverageReturn -51.354 +Average/Iteration 234 +Average/MaxReturn -41.0632 +Average/MinReturn -72.6134 +Average/NumEpisodes 120 +Average/StdReturn 5.19536 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83269 +GaussianMLPPolicy/KLAfter 0.00324489 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000104221 +GaussianMLPPolicy/LossBefore 1.39078e-09 +GaussianMLPPolicy/dLoss -0.000104219 +Iteration 234 +MetaTest/Average/AverageDiscountedReturn -50.2024 +MetaTest/Average/AverageReturn -50.2024 +MetaTest/Average/Iteration 234 +MetaTest/Average/MaxReturn -42.4582 +MetaTest/Average/MinReturn -59.5724 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.60811 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2024 +MetaTest/__unnamed_task__/AverageReturn -50.2024 +MetaTest/__unnamed_task__/Iteration 234 +MetaTest/__unnamed_task__/MaxReturn -42.4582 +MetaTest/__unnamed_task__/MinReturn -59.5724 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.60811 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.128e+07 +__unnamed_task__/AverageDiscountedReturn -29.0446 +__unnamed_task__/AverageReturn -51.354 +__unnamed_task__/Iteration 234 +__unnamed_task__/MaxReturn -41.0632 +__unnamed_task__/MinReturn -72.6134 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.19536 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 07:42:29 | [maml_trainer] epoch #235 | Sampling for adapation and meta-testing... +2025-04-08 07:46:21 | [maml_trainer] epoch #235 | Finished meta-testing... +2025-04-08 07:46:21 | [maml_trainer] epoch #235 | Saving snapshot... +2025-04-08 07:46:42 | [maml_trainer] epoch #235 | Saved +2025-04-08 07:46:42 | [maml_trainer] epoch #235 | Time 400046.80 s +2025-04-08 07:46:42 | [maml_trainer] epoch #235 | EpochTime 1675.54 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.2365 +Average/AverageReturn -51.9828 +Average/Iteration 235 +Average/MaxReturn -42.4261 +Average/MinReturn -68.2036 +Average/NumEpisodes 120 +Average/StdReturn 4.69304 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82896 +GaussianMLPPolicy/KLAfter 0.00395181 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000156514 +GaussianMLPPolicy/LossBefore 6.15915e-09 +GaussianMLPPolicy/dLoss -0.000156507 +Iteration 235 +MetaTest/Average/AverageDiscountedReturn -50.7603 +MetaTest/Average/AverageReturn -50.7603 +MetaTest/Average/Iteration 235 +MetaTest/Average/MaxReturn -42.5149 +MetaTest/Average/MinReturn -69.5694 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.87698 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.7603 +MetaTest/__unnamed_task__/AverageReturn -50.7603 +MetaTest/__unnamed_task__/Iteration 235 +MetaTest/__unnamed_task__/MaxReturn -42.5149 +MetaTest/__unnamed_task__/MinReturn -69.5694 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.87698 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1328e+07 +__unnamed_task__/AverageDiscountedReturn -29.2365 +__unnamed_task__/AverageReturn -51.9828 +__unnamed_task__/Iteration 235 +__unnamed_task__/MaxReturn -42.4261 +__unnamed_task__/MinReturn -68.2036 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.69304 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 08:10:09 | [maml_trainer] epoch #236 | Sampling for adapation and meta-testing... +2025-04-08 08:14:04 | [maml_trainer] epoch #236 | Finished meta-testing... +2025-04-08 08:14:04 | [maml_trainer] epoch #236 | Saving snapshot... +2025-04-08 08:14:25 | [maml_trainer] epoch #236 | Saved +2025-04-08 08:14:25 | [maml_trainer] epoch #236 | Time 401709.90 s +2025-04-08 08:14:25 | [maml_trainer] epoch #236 | EpochTime 1663.09 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5871 +Average/AverageReturn -50.7911 +Average/Iteration 236 +Average/MaxReturn -40.5226 +Average/MinReturn -71.4503 +Average/NumEpisodes 120 +Average/StdReturn 5.55317 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82669 +GaussianMLPPolicy/KLAfter 0.00274492 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.59901e-05 +GaussianMLPPolicy/LossBefore 1.3272e-08 +GaussianMLPPolicy/dLoss -1.59768e-05 +Iteration 236 +MetaTest/Average/AverageDiscountedReturn -49.7591 +MetaTest/Average/AverageReturn -49.7591 +MetaTest/Average/Iteration 236 +MetaTest/Average/MaxReturn -41.9622 +MetaTest/Average/MinReturn -61.8325 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.11553 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7591 +MetaTest/__unnamed_task__/AverageReturn -49.7591 +MetaTest/__unnamed_task__/Iteration 236 +MetaTest/__unnamed_task__/MaxReturn -41.9622 +MetaTest/__unnamed_task__/MinReturn -61.8325 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.11553 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1376e+07 +__unnamed_task__/AverageDiscountedReturn -28.5871 +__unnamed_task__/AverageReturn -50.7911 +__unnamed_task__/Iteration 236 +__unnamed_task__/MaxReturn -40.5226 +__unnamed_task__/MinReturn -71.4503 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.55317 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 08:37:41 | [maml_trainer] epoch #237 | Sampling for adapation and meta-testing... +2025-04-08 08:41:36 | [maml_trainer] epoch #237 | Finished meta-testing... +2025-04-08 08:41:36 | [maml_trainer] epoch #237 | Saving snapshot... +2025-04-08 08:41:58 | [maml_trainer] epoch #237 | Saved +2025-04-08 08:41:58 | [maml_trainer] epoch #237 | Time 403361.99 s +2025-04-08 08:41:58 | [maml_trainer] epoch #237 | EpochTime 1652.09 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.9405 +Average/AverageReturn -50.6949 +Average/Iteration 237 +Average/MaxReturn 204.397 +Average/MinReturn -69.5446 +Average/NumEpisodes 120 +Average/StdReturn 24.0232 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82337 +GaussianMLPPolicy/KLAfter 0.00297702 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.12971e-05 +GaussianMLPPolicy/LossBefore -7.15256e-10 +GaussianMLPPolicy/dLoss 4.12964e-05 +Iteration 237 +MetaTest/Average/AverageDiscountedReturn -51.091 +MetaTest/Average/AverageReturn -51.091 +MetaTest/Average/Iteration 237 +MetaTest/Average/MaxReturn -44.9536 +MetaTest/Average/MinReturn -58.9656 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.47283 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.091 +MetaTest/__unnamed_task__/AverageReturn -51.091 +MetaTest/__unnamed_task__/Iteration 237 +MetaTest/__unnamed_task__/MaxReturn -44.9536 +MetaTest/__unnamed_task__/MinReturn -58.9656 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.47283 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1424e+07 +__unnamed_task__/AverageDiscountedReturn -28.9405 +__unnamed_task__/AverageReturn -50.6949 +__unnamed_task__/Iteration 237 +__unnamed_task__/MaxReturn 204.397 +__unnamed_task__/MinReturn -69.5446 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 24.0232 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 09:05:31 | [maml_trainer] epoch #238 | Sampling for adapation and meta-testing... +2025-04-08 09:09:28 | [maml_trainer] epoch #238 | Finished meta-testing... +2025-04-08 09:09:28 | [maml_trainer] epoch #238 | Saving snapshot... +2025-04-08 09:09:50 | [maml_trainer] epoch #238 | Saved +2025-04-08 09:09:50 | [maml_trainer] epoch #238 | Time 405034.50 s +2025-04-08 09:09:50 | [maml_trainer] epoch #238 | EpochTime 1672.50 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9844 +Average/AverageReturn -52.7487 +Average/Iteration 238 +Average/MaxReturn -40.236 +Average/MinReturn -133.06 +Average/NumEpisodes 120 +Average/StdReturn 10.1212 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81901 +GaussianMLPPolicy/KLAfter 0.00194427 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.7522e-05 +GaussianMLPPolicy/LossBefore -3.97364e-11 +GaussianMLPPolicy/dLoss -8.7522e-05 +Iteration 238 +MetaTest/Average/AverageDiscountedReturn -52.9153 +MetaTest/Average/AverageReturn -52.9153 +MetaTest/Average/Iteration 238 +MetaTest/Average/MaxReturn -44.6373 +MetaTest/Average/MinReturn -64.6056 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.06248 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.9153 +MetaTest/__unnamed_task__/AverageReturn -52.9153 +MetaTest/__unnamed_task__/Iteration 238 +MetaTest/__unnamed_task__/MaxReturn -44.6373 +MetaTest/__unnamed_task__/MinReturn -64.6056 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.06248 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1472e+07 +__unnamed_task__/AverageDiscountedReturn -28.9844 +__unnamed_task__/AverageReturn -52.7487 +__unnamed_task__/Iteration 238 +__unnamed_task__/MaxReturn -40.236 +__unnamed_task__/MinReturn -133.06 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.1212 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 09:33:27 | [maml_trainer] epoch #239 | Sampling for adapation and meta-testing... +2025-04-08 09:37:21 | [maml_trainer] epoch #239 | Finished meta-testing... +2025-04-08 09:37:21 | [maml_trainer] epoch #239 | Saving snapshot... +2025-04-08 09:37:43 | [maml_trainer] epoch #239 | Saved +2025-04-08 09:37:43 | [maml_trainer] epoch #239 | Time 406707.44 s +2025-04-08 09:37:43 | [maml_trainer] epoch #239 | EpochTime 1672.94 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -29.0641 +Average/AverageReturn -52.5882 +Average/Iteration 239 +Average/MaxReturn -42.5082 +Average/MinReturn -70.5259 +Average/NumEpisodes 120 +Average/StdReturn 6.15243 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81607 +GaussianMLPPolicy/KLAfter 0.0012625 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.50259e-05 +GaussianMLPPolicy/LossBefore 8.74201e-10 +GaussianMLPPolicy/dLoss 6.50268e-05 +Iteration 239 +MetaTest/Average/AverageDiscountedReturn -50.8816 +MetaTest/Average/AverageReturn -50.8816 +MetaTest/Average/Iteration 239 +MetaTest/Average/MaxReturn -41.6194 +MetaTest/Average/MinReturn -59.7724 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.22666 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8816 +MetaTest/__unnamed_task__/AverageReturn -50.8816 +MetaTest/__unnamed_task__/Iteration 239 +MetaTest/__unnamed_task__/MaxReturn -41.6194 +MetaTest/__unnamed_task__/MinReturn -59.7724 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.22666 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.152e+07 +__unnamed_task__/AverageDiscountedReturn -29.0641 +__unnamed_task__/AverageReturn -52.5882 +__unnamed_task__/Iteration 239 +__unnamed_task__/MaxReturn -42.5082 +__unnamed_task__/MinReturn -70.5259 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.15243 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 10:01:15 | [maml_trainer] epoch #240 | Sampling for adapation and meta-testing... +2025-04-08 10:05:20 | [maml_trainer] epoch #240 | Finished meta-testing... +2025-04-08 10:05:20 | [maml_trainer] epoch #240 | Saving snapshot... +2025-04-08 10:05:43 | [maml_trainer] epoch #240 | Saved +2025-04-08 10:05:43 | [maml_trainer] epoch #240 | Time 408387.95 s +2025-04-08 10:05:43 | [maml_trainer] epoch #240 | EpochTime 1680.51 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -29.2563 +Average/AverageReturn -53.8642 +Average/Iteration 240 +Average/MaxReturn -41.6887 +Average/MinReturn -173.623 +Average/NumEpisodes 120 +Average/StdReturn 13.1301 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81342 +GaussianMLPPolicy/KLAfter 0.00177441 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.99203e-06 +GaussianMLPPolicy/LossBefore 1.49012e-09 +GaussianMLPPolicy/dLoss -4.99054e-06 +Iteration 240 +MetaTest/Average/AverageDiscountedReturn -50.5434 +MetaTest/Average/AverageReturn -50.5434 +MetaTest/Average/Iteration 240 +MetaTest/Average/MaxReturn -42.0598 +MetaTest/Average/MinReturn -61.4803 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.61384 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5434 +MetaTest/__unnamed_task__/AverageReturn -50.5434 +MetaTest/__unnamed_task__/Iteration 240 +MetaTest/__unnamed_task__/MaxReturn -42.0598 +MetaTest/__unnamed_task__/MinReturn -61.4803 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.61384 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1568e+07 +__unnamed_task__/AverageDiscountedReturn -29.2563 +__unnamed_task__/AverageReturn -53.8642 +__unnamed_task__/Iteration 240 +__unnamed_task__/MaxReturn -41.6887 +__unnamed_task__/MinReturn -173.623 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.1301 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-08 10:30:27 | [maml_trainer] epoch #241 | Sampling for adapation and meta-testing... +2025-04-08 10:34:36 | [maml_trainer] epoch #241 | Finished meta-testing... +2025-04-08 10:34:36 | [maml_trainer] epoch #241 | Saving snapshot... +2025-04-08 10:35:00 | [maml_trainer] epoch #241 | Saved +2025-04-08 10:35:00 | [maml_trainer] epoch #241 | Time 410144.38 s +2025-04-08 10:35:00 | [maml_trainer] epoch #241 | EpochTime 1756.42 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3258 +Average/AverageReturn -50.5161 +Average/Iteration 241 +Average/MaxReturn -42.0889 +Average/MinReturn -69.8231 +Average/NumEpisodes 120 +Average/StdReturn 5.23293 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81152 +GaussianMLPPolicy/KLAfter 0.00129788 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.37611e-07 +GaussianMLPPolicy/LossBefore 8.82149e-09 +GaussianMLPPolicy/dLoss -6.28789e-07 +Iteration 241 +MetaTest/Average/AverageDiscountedReturn -52.6926 +MetaTest/Average/AverageReturn -52.6926 +MetaTest/Average/Iteration 241 +MetaTest/Average/MaxReturn -42.9669 +MetaTest/Average/MinReturn -70.8061 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.52521 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6926 +MetaTest/__unnamed_task__/AverageReturn -52.6926 +MetaTest/__unnamed_task__/Iteration 241 +MetaTest/__unnamed_task__/MaxReturn -42.9669 +MetaTest/__unnamed_task__/MinReturn -70.8061 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.52521 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1616e+07 +__unnamed_task__/AverageDiscountedReturn -28.3258 +__unnamed_task__/AverageReturn -50.5161 +__unnamed_task__/Iteration 241 +__unnamed_task__/MaxReturn -42.0889 +__unnamed_task__/MinReturn -69.8231 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.23293 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 10:59:40 | [maml_trainer] epoch #242 | Sampling for adapation and meta-testing... +2025-04-08 11:03:45 | [maml_trainer] epoch #242 | Finished meta-testing... +2025-04-08 11:03:45 | [maml_trainer] epoch #242 | Saving snapshot... +2025-04-08 11:04:09 | [maml_trainer] epoch #242 | Saved +2025-04-08 11:04:09 | [maml_trainer] epoch #242 | Time 411893.37 s +2025-04-08 11:04:09 | [maml_trainer] epoch #242 | EpochTime 1748.98 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.758 +Average/AverageReturn -51.9033 +Average/Iteration 242 +Average/MaxReturn -42.0154 +Average/MinReturn -67.6078 +Average/NumEpisodes 120 +Average/StdReturn 5.72807 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81028 +GaussianMLPPolicy/KLAfter 0.000995313 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.43395e-05 +GaussianMLPPolicy/LossBefore -6.19888e-09 +GaussianMLPPolicy/dLoss 1.43333e-05 +Iteration 242 +MetaTest/Average/AverageDiscountedReturn -52.6808 +MetaTest/Average/AverageReturn -52.6808 +MetaTest/Average/Iteration 242 +MetaTest/Average/MaxReturn -45.9137 +MetaTest/Average/MinReturn -70.3188 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.49793 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6808 +MetaTest/__unnamed_task__/AverageReturn -52.6808 +MetaTest/__unnamed_task__/Iteration 242 +MetaTest/__unnamed_task__/MaxReturn -45.9137 +MetaTest/__unnamed_task__/MinReturn -70.3188 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.49793 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1664e+07 +__unnamed_task__/AverageDiscountedReturn -28.758 +__unnamed_task__/AverageReturn -51.9033 +__unnamed_task__/Iteration 242 +__unnamed_task__/MaxReturn -42.0154 +__unnamed_task__/MinReturn -67.6078 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.72807 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 11:29:01 | [maml_trainer] epoch #243 | Sampling for adapation and meta-testing... +2025-04-08 11:33:13 | [maml_trainer] epoch #243 | Finished meta-testing... +2025-04-08 11:33:13 | [maml_trainer] epoch #243 | Saving snapshot... +2025-04-08 11:33:37 | [maml_trainer] epoch #243 | Saved +2025-04-08 11:33:37 | [maml_trainer] epoch #243 | Time 413661.20 s +2025-04-08 11:33:37 | [maml_trainer] epoch #243 | EpochTime 1767.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6457 +Average/AverageReturn -51.5362 +Average/Iteration 243 +Average/MaxReturn -42.4751 +Average/MinReturn -68.3209 +Average/NumEpisodes 120 +Average/StdReturn 5.03247 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8102 +GaussianMLPPolicy/KLAfter 0.00114557 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.36318e-05 +GaussianMLPPolicy/LossBefore 5.32468e-09 +GaussianMLPPolicy/dLoss 3.36371e-05 +Iteration 243 +MetaTest/Average/AverageDiscountedReturn -52.2185 +MetaTest/Average/AverageReturn -52.2185 +MetaTest/Average/Iteration 243 +MetaTest/Average/MaxReturn -44.519 +MetaTest/Average/MinReturn -62.0051 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.97425 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2185 +MetaTest/__unnamed_task__/AverageReturn -52.2185 +MetaTest/__unnamed_task__/Iteration 243 +MetaTest/__unnamed_task__/MaxReturn -44.519 +MetaTest/__unnamed_task__/MinReturn -62.0051 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.97425 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1712e+07 +__unnamed_task__/AverageDiscountedReturn -28.6457 +__unnamed_task__/AverageReturn -51.5362 +__unnamed_task__/Iteration 243 +__unnamed_task__/MaxReturn -42.4751 +__unnamed_task__/MinReturn -68.3209 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.03247 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 11:58:26 | [maml_trainer] epoch #244 | Sampling for adapation and meta-testing... +2025-04-08 12:02:27 | [maml_trainer] epoch #244 | Finished meta-testing... +2025-04-08 12:02:27 | [maml_trainer] epoch #244 | Saving snapshot... +2025-04-08 12:02:50 | [maml_trainer] epoch #244 | Saved +2025-04-08 12:02:50 | [maml_trainer] epoch #244 | Time 415414.47 s +2025-04-08 12:02:50 | [maml_trainer] epoch #244 | EpochTime 1753.26 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5324 +Average/AverageReturn -51.3588 +Average/Iteration 244 +Average/MaxReturn -42.8646 +Average/MinReturn -71.0507 +Average/NumEpisodes 120 +Average/StdReturn 4.51158 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81066 +GaussianMLPPolicy/KLAfter 0.00183725 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.30579e-05 +GaussianMLPPolicy/LossBefore 1.95901e-08 +GaussianMLPPolicy/dLoss 9.30775e-05 +Iteration 244 +MetaTest/Average/AverageDiscountedReturn -52.6962 +MetaTest/Average/AverageReturn -52.6962 +MetaTest/Average/Iteration 244 +MetaTest/Average/MaxReturn -44.9474 +MetaTest/Average/MinReturn -72.5132 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.65362 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6962 +MetaTest/__unnamed_task__/AverageReturn -52.6962 +MetaTest/__unnamed_task__/Iteration 244 +MetaTest/__unnamed_task__/MaxReturn -44.9474 +MetaTest/__unnamed_task__/MinReturn -72.5132 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.65362 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.176e+07 +__unnamed_task__/AverageDiscountedReturn -28.5324 +__unnamed_task__/AverageReturn -51.3588 +__unnamed_task__/Iteration 244 +__unnamed_task__/MaxReturn -42.8646 +__unnamed_task__/MinReturn -71.0507 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.51158 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 12:27:40 | [maml_trainer] epoch #245 | Sampling for adapation and meta-testing... +2025-04-08 12:31:49 | [maml_trainer] epoch #245 | Finished meta-testing... +2025-04-08 12:31:49 | [maml_trainer] epoch #245 | Saving snapshot... +2025-04-08 12:32:12 | [maml_trainer] epoch #245 | Saved +2025-04-08 12:32:12 | [maml_trainer] epoch #245 | Time 417176.79 s +2025-04-08 12:32:12 | [maml_trainer] epoch #245 | EpochTime 1762.31 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8971 +Average/AverageReturn -51.8676 +Average/Iteration 245 +Average/MaxReturn -42.8434 +Average/MinReturn -66.3916 +Average/NumEpisodes 120 +Average/StdReturn 4.83858 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81103 +GaussianMLPPolicy/KLAfter 0.00217185 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.96368e-05 +GaussianMLPPolicy/LossBefore -1.73648e-08 +GaussianMLPPolicy/dLoss -6.96541e-05 +Iteration 245 +MetaTest/Average/AverageDiscountedReturn -53.0855 +MetaTest/Average/AverageReturn -53.0855 +MetaTest/Average/Iteration 245 +MetaTest/Average/MaxReturn -45.4076 +MetaTest/Average/MinReturn -68.2465 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.27092 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.0855 +MetaTest/__unnamed_task__/AverageReturn -53.0855 +MetaTest/__unnamed_task__/Iteration 245 +MetaTest/__unnamed_task__/MaxReturn -45.4076 +MetaTest/__unnamed_task__/MinReturn -68.2465 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.27092 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1808e+07 +__unnamed_task__/AverageDiscountedReturn -28.8971 +__unnamed_task__/AverageReturn -51.8676 +__unnamed_task__/Iteration 245 +__unnamed_task__/MaxReturn -42.8434 +__unnamed_task__/MinReturn -66.3916 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.83858 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 12:56:44 | [maml_trainer] epoch #246 | Sampling for adapation and meta-testing... +2025-04-08 13:00:48 | [maml_trainer] epoch #246 | Finished meta-testing... +2025-04-08 13:00:48 | [maml_trainer] epoch #246 | Saving snapshot... +2025-04-08 13:01:11 | [maml_trainer] epoch #246 | Saved +2025-04-08 13:01:12 | [maml_trainer] epoch #246 | Time 418915.96 s +2025-04-08 13:01:12 | [maml_trainer] epoch #246 | EpochTime 1739.17 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8496 +Average/AverageReturn -51.9471 +Average/Iteration 246 +Average/MaxReturn -42.644 +Average/MinReturn -70.591 +Average/NumEpisodes 120 +Average/StdReturn 4.87934 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81204 +GaussianMLPPolicy/KLAfter 0.00139245 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.37056e-05 +GaussianMLPPolicy/LossBefore 9.57648e-09 +GaussianMLPPolicy/dLoss 6.37152e-05 +Iteration 246 +MetaTest/Average/AverageDiscountedReturn -51.8971 +MetaTest/Average/AverageReturn -51.8971 +MetaTest/Average/Iteration 246 +MetaTest/Average/MaxReturn -45.6898 +MetaTest/Average/MinReturn -61.1031 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.54753 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8971 +MetaTest/__unnamed_task__/AverageReturn -51.8971 +MetaTest/__unnamed_task__/Iteration 246 +MetaTest/__unnamed_task__/MaxReturn -45.6898 +MetaTest/__unnamed_task__/MinReturn -61.1031 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.54753 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1856e+07 +__unnamed_task__/AverageDiscountedReturn -28.8496 +__unnamed_task__/AverageReturn -51.9471 +__unnamed_task__/Iteration 246 +__unnamed_task__/MaxReturn -42.644 +__unnamed_task__/MinReturn -70.591 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.87934 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 13:25:51 | [maml_trainer] epoch #247 | Sampling for adapation and meta-testing... +2025-04-08 13:30:01 | [maml_trainer] epoch #247 | Finished meta-testing... +2025-04-08 13:30:01 | [maml_trainer] epoch #247 | Saving snapshot... +2025-04-08 13:30:25 | [maml_trainer] epoch #247 | Saved +2025-04-08 13:30:25 | [maml_trainer] epoch #247 | Time 420669.11 s +2025-04-08 13:30:25 | [maml_trainer] epoch #247 | EpochTime 1753.14 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3966 +Average/AverageReturn -51.0771 +Average/Iteration 247 +Average/MaxReturn -42.5162 +Average/MinReturn -67.771 +Average/NumEpisodes 120 +Average/StdReturn 4.70585 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81331 +GaussianMLPPolicy/KLAfter 0.00169087 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.37875e-05 +GaussianMLPPolicy/LossBefore 3.53654e-09 +GaussianMLPPolicy/dLoss 2.3791e-05 +Iteration 247 +MetaTest/Average/AverageDiscountedReturn -51.1159 +MetaTest/Average/AverageReturn -51.1159 +MetaTest/Average/Iteration 247 +MetaTest/Average/MaxReturn -43.8615 +MetaTest/Average/MinReturn -60.7264 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.02631 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1159 +MetaTest/__unnamed_task__/AverageReturn -51.1159 +MetaTest/__unnamed_task__/Iteration 247 +MetaTest/__unnamed_task__/MaxReturn -43.8615 +MetaTest/__unnamed_task__/MinReturn -60.7264 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.02631 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1904e+07 +__unnamed_task__/AverageDiscountedReturn -28.3966 +__unnamed_task__/AverageReturn -51.0771 +__unnamed_task__/Iteration 247 +__unnamed_task__/MaxReturn -42.5162 +__unnamed_task__/MinReturn -67.771 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.70585 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 13:54:47 | [maml_trainer] epoch #248 | Sampling for adapation and meta-testing... +2025-04-08 13:58:53 | [maml_trainer] epoch #248 | Finished meta-testing... +2025-04-08 13:58:53 | [maml_trainer] epoch #248 | Saving snapshot... +2025-04-08 13:59:17 | [maml_trainer] epoch #248 | Saved +2025-04-08 13:59:17 | [maml_trainer] epoch #248 | Time 422401.25 s +2025-04-08 13:59:17 | [maml_trainer] epoch #248 | EpochTime 1732.14 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2892 +Average/AverageReturn -50.7719 +Average/Iteration 248 +Average/MaxReturn -44.4334 +Average/MinReturn -66.0031 +Average/NumEpisodes 120 +Average/StdReturn 4.52102 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81435 +GaussianMLPPolicy/KLAfter 0.001917 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.64176e-05 +GaussianMLPPolicy/LossBefore -4.17232e-09 +GaussianMLPPolicy/dLoss -4.64217e-05 +Iteration 248 +MetaTest/Average/AverageDiscountedReturn -51.3849 +MetaTest/Average/AverageReturn -51.3849 +MetaTest/Average/Iteration 248 +MetaTest/Average/MaxReturn -41.2253 +MetaTest/Average/MinReturn -60.8753 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.00403 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3849 +MetaTest/__unnamed_task__/AverageReturn -51.3849 +MetaTest/__unnamed_task__/Iteration 248 +MetaTest/__unnamed_task__/MaxReturn -41.2253 +MetaTest/__unnamed_task__/MinReturn -60.8753 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.00403 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.1952e+07 +__unnamed_task__/AverageDiscountedReturn -28.2892 +__unnamed_task__/AverageReturn -50.7719 +__unnamed_task__/Iteration 248 +__unnamed_task__/MaxReturn -44.4334 +__unnamed_task__/MinReturn -66.0031 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.52102 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 14:24:14 | [maml_trainer] epoch #249 | Sampling for adapation and meta-testing... +2025-04-08 14:28:21 | [maml_trainer] epoch #249 | Finished meta-testing... +2025-04-08 14:28:21 | [maml_trainer] epoch #249 | Saving snapshot... +2025-04-08 14:28:44 | [maml_trainer] epoch #249 | Saved +2025-04-08 14:28:44 | [maml_trainer] epoch #249 | Time 424168.50 s +2025-04-08 14:28:44 | [maml_trainer] epoch #249 | EpochTime 1767.24 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4008 +Average/AverageReturn -51.3808 +Average/Iteration 249 +Average/MaxReturn -42.0878 +Average/MinReturn -74.4523 +Average/NumEpisodes 120 +Average/StdReturn 5.21937 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81527 +GaussianMLPPolicy/KLAfter 0.00274183 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.02061e-05 +GaussianMLPPolicy/LossBefore -3.29812e-09 +GaussianMLPPolicy/dLoss -6.02094e-05 +Iteration 249 +MetaTest/Average/AverageDiscountedReturn -50.9708 +MetaTest/Average/AverageReturn -50.9708 +MetaTest/Average/Iteration 249 +MetaTest/Average/MaxReturn -43.8587 +MetaTest/Average/MinReturn -64.4352 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.9183 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9708 +MetaTest/__unnamed_task__/AverageReturn -50.9708 +MetaTest/__unnamed_task__/Iteration 249 +MetaTest/__unnamed_task__/MaxReturn -43.8587 +MetaTest/__unnamed_task__/MinReturn -64.4352 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.9183 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2e+07 +__unnamed_task__/AverageDiscountedReturn -28.4008 +__unnamed_task__/AverageReturn -51.3808 +__unnamed_task__/Iteration 249 +__unnamed_task__/MaxReturn -42.0878 +__unnamed_task__/MinReturn -74.4523 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.21937 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 14:53:33 | [maml_trainer] epoch #250 | Sampling for adapation and meta-testing... +2025-04-08 14:57:41 | [maml_trainer] epoch #250 | Finished meta-testing... +2025-04-08 14:57:41 | [maml_trainer] epoch #250 | Saving snapshot... +2025-04-08 14:58:04 | [maml_trainer] epoch #250 | Saved +2025-04-08 14:58:04 | [maml_trainer] epoch #250 | Time 425928.62 s +2025-04-08 14:58:04 | [maml_trainer] epoch #250 | EpochTime 1760.12 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6213 +Average/AverageReturn -51.8056 +Average/Iteration 250 +Average/MaxReturn -42.6204 +Average/MinReturn -69.1461 +Average/NumEpisodes 120 +Average/StdReturn 5.65102 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81622 +GaussianMLPPolicy/KLAfter 0.000972581 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.49136e-05 +GaussianMLPPolicy/LossBefore -1.0252e-08 +GaussianMLPPolicy/dLoss 1.49033e-05 +Iteration 250 +MetaTest/Average/AverageDiscountedReturn -50.5035 +MetaTest/Average/AverageReturn -50.5035 +MetaTest/Average/Iteration 250 +MetaTest/Average/MaxReturn -43.6657 +MetaTest/Average/MinReturn -64.7145 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.37656 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5035 +MetaTest/__unnamed_task__/AverageReturn -50.5035 +MetaTest/__unnamed_task__/Iteration 250 +MetaTest/__unnamed_task__/MaxReturn -43.6657 +MetaTest/__unnamed_task__/MinReturn -64.7145 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.37656 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2048e+07 +__unnamed_task__/AverageDiscountedReturn -28.6213 +__unnamed_task__/AverageReturn -51.8056 +__unnamed_task__/Iteration 250 +__unnamed_task__/MaxReturn -42.6204 +__unnamed_task__/MinReturn -69.1461 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.65102 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 15:22:58 | [maml_trainer] epoch #251 | Sampling for adapation and meta-testing... +2025-04-08 15:27:08 | [maml_trainer] epoch #251 | Finished meta-testing... +2025-04-08 15:27:08 | [maml_trainer] epoch #251 | Saving snapshot... +2025-04-08 15:27:32 | [maml_trainer] epoch #251 | Saved +2025-04-08 15:27:32 | [maml_trainer] epoch #251 | Time 427696.10 s +2025-04-08 15:27:32 | [maml_trainer] epoch #251 | EpochTime 1767.48 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3626 +Average/AverageReturn -51.3339 +Average/Iteration 251 +Average/MaxReturn -40.8979 +Average/MinReturn -65.9368 +Average/NumEpisodes 120 +Average/StdReturn 4.42577 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81686 +GaussianMLPPolicy/KLAfter 0.000680749 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.97689e-05 +GaussianMLPPolicy/LossBefore -6.15915e-09 +GaussianMLPPolicy/dLoss 7.97627e-05 +Iteration 251 +MetaTest/Average/AverageDiscountedReturn -51.7466 +MetaTest/Average/AverageReturn -51.7466 +MetaTest/Average/Iteration 251 +MetaTest/Average/MaxReturn -42.3409 +MetaTest/Average/MinReturn -68.7625 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.69011 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7466 +MetaTest/__unnamed_task__/AverageReturn -51.7466 +MetaTest/__unnamed_task__/Iteration 251 +MetaTest/__unnamed_task__/MaxReturn -42.3409 +MetaTest/__unnamed_task__/MinReturn -68.7625 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.69011 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2096e+07 +__unnamed_task__/AverageDiscountedReturn -28.3626 +__unnamed_task__/AverageReturn -51.3339 +__unnamed_task__/Iteration 251 +__unnamed_task__/MaxReturn -40.8979 +__unnamed_task__/MinReturn -65.9368 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.42577 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 15:51:30 | [maml_trainer] epoch #252 | Sampling for adapation and meta-testing... +2025-04-08 15:55:22 | [maml_trainer] epoch #252 | Finished meta-testing... +2025-04-08 15:55:22 | [maml_trainer] epoch #252 | Saving snapshot... +2025-04-08 15:55:44 | [maml_trainer] epoch #252 | Saved +2025-04-08 15:55:44 | [maml_trainer] epoch #252 | Time 429388.29 s +2025-04-08 15:55:44 | [maml_trainer] epoch #252 | EpochTime 1692.19 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2482 +Average/AverageReturn -50.9791 +Average/Iteration 252 +Average/MaxReturn -42.3311 +Average/MinReturn -67.2909 +Average/NumEpisodes 120 +Average/StdReturn 5.00657 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81715 +GaussianMLPPolicy/KLAfter 0.00144024 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.90339e-05 +GaussianMLPPolicy/LossBefore -8.74202e-10 +GaussianMLPPolicy/dLoss 3.9033e-05 +Iteration 252 +MetaTest/Average/AverageDiscountedReturn -52.2337 +MetaTest/Average/AverageReturn -52.2337 +MetaTest/Average/Iteration 252 +MetaTest/Average/MaxReturn -43.4874 +MetaTest/Average/MinReturn -65.9009 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.60654 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2337 +MetaTest/__unnamed_task__/AverageReturn -52.2337 +MetaTest/__unnamed_task__/Iteration 252 +MetaTest/__unnamed_task__/MaxReturn -43.4874 +MetaTest/__unnamed_task__/MinReturn -65.9009 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.60654 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2144e+07 +__unnamed_task__/AverageDiscountedReturn -28.2482 +__unnamed_task__/AverageReturn -50.9791 +__unnamed_task__/Iteration 252 +__unnamed_task__/MaxReturn -42.3311 +__unnamed_task__/MinReturn -67.2909 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.00657 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 16:18:53 | [maml_trainer] epoch #253 | Sampling for adapation and meta-testing... +2025-04-08 16:22:48 | [maml_trainer] epoch #253 | Finished meta-testing... +2025-04-08 16:22:48 | [maml_trainer] epoch #253 | Saving snapshot... +2025-04-08 16:23:10 | [maml_trainer] epoch #253 | Saved +2025-04-08 16:23:10 | [maml_trainer] epoch #253 | Time 431034.44 s +2025-04-08 16:23:10 | [maml_trainer] epoch #253 | EpochTime 1646.15 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1791 +Average/AverageReturn -51.0506 +Average/Iteration 253 +Average/MaxReturn -40.1196 +Average/MinReturn -71.9114 +Average/NumEpisodes 120 +Average/StdReturn 5.65183 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81644 +GaussianMLPPolicy/KLAfter 0.00213596 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.24239e-05 +GaussianMLPPolicy/LossBefore -4.21206e-09 +GaussianMLPPolicy/dLoss -2.24282e-05 +Iteration 253 +MetaTest/Average/AverageDiscountedReturn -51.9997 +MetaTest/Average/AverageReturn -51.9997 +MetaTest/Average/Iteration 253 +MetaTest/Average/MaxReturn -42.577 +MetaTest/Average/MinReturn -64.6295 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.60955 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.9997 +MetaTest/__unnamed_task__/AverageReturn -51.9997 +MetaTest/__unnamed_task__/Iteration 253 +MetaTest/__unnamed_task__/MaxReturn -42.577 +MetaTest/__unnamed_task__/MinReturn -64.6295 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.60955 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2192e+07 +__unnamed_task__/AverageDiscountedReturn -28.1791 +__unnamed_task__/AverageReturn -51.0506 +__unnamed_task__/Iteration 253 +__unnamed_task__/MaxReturn -40.1196 +__unnamed_task__/MinReturn -71.9114 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.65183 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 16:46:27 | [maml_trainer] epoch #254 | Sampling for adapation and meta-testing... +2025-04-08 16:50:21 | [maml_trainer] epoch #254 | Finished meta-testing... +2025-04-08 16:50:21 | [maml_trainer] epoch #254 | Saving snapshot... +2025-04-08 16:50:43 | [maml_trainer] epoch #254 | Saved +2025-04-08 16:50:43 | [maml_trainer] epoch #254 | Time 432687.65 s +2025-04-08 16:50:43 | [maml_trainer] epoch #254 | EpochTime 1653.21 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0026 +Average/AverageReturn -49.8377 +Average/Iteration 254 +Average/MaxReturn -40.3218 +Average/MinReturn -63.0763 +Average/NumEpisodes 120 +Average/StdReturn 4.43879 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81587 +GaussianMLPPolicy/KLAfter 0.00239185 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.75177e-05 +GaussianMLPPolicy/LossBefore -4.64916e-09 +GaussianMLPPolicy/dLoss -8.75223e-05 +Iteration 254 +MetaTest/Average/AverageDiscountedReturn -51.037 +MetaTest/Average/AverageReturn -51.037 +MetaTest/Average/Iteration 254 +MetaTest/Average/MaxReturn -43.8149 +MetaTest/Average/MinReturn -64.1023 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.07655 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.037 +MetaTest/__unnamed_task__/AverageReturn -51.037 +MetaTest/__unnamed_task__/Iteration 254 +MetaTest/__unnamed_task__/MaxReturn -43.8149 +MetaTest/__unnamed_task__/MinReturn -64.1023 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.07655 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.224e+07 +__unnamed_task__/AverageDiscountedReturn -28.0026 +__unnamed_task__/AverageReturn -49.8377 +__unnamed_task__/Iteration 254 +__unnamed_task__/MaxReturn -40.3218 +__unnamed_task__/MinReturn -63.0763 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.43879 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 17:14:06 | [maml_trainer] epoch #255 | Sampling for adapation and meta-testing... +2025-04-08 17:18:00 | [maml_trainer] epoch #255 | Finished meta-testing... +2025-04-08 17:18:00 | [maml_trainer] epoch #255 | Saving snapshot... +2025-04-08 17:18:22 | [maml_trainer] epoch #255 | Saved +2025-04-08 17:18:22 | [maml_trainer] epoch #255 | Time 434346.65 s +2025-04-08 17:18:22 | [maml_trainer] epoch #255 | EpochTime 1659.00 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2086 +Average/AverageReturn -50.9134 +Average/Iteration 255 +Average/MaxReturn -40.158 +Average/MinReturn -66.3933 +Average/NumEpisodes 120 +Average/StdReturn 4.88822 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81489 +GaussianMLPPolicy/KLAfter 0.00383516 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.66121e-05 +GaussianMLPPolicy/LossBefore -1.75238e-08 +GaussianMLPPolicy/dLoss -3.66296e-05 +Iteration 255 +MetaTest/Average/AverageDiscountedReturn -50.3645 +MetaTest/Average/AverageReturn -50.3645 +MetaTest/Average/Iteration 255 +MetaTest/Average/MaxReturn -42.6142 +MetaTest/Average/MinReturn -68.0418 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.34433 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.3645 +MetaTest/__unnamed_task__/AverageReturn -50.3645 +MetaTest/__unnamed_task__/Iteration 255 +MetaTest/__unnamed_task__/MaxReturn -42.6142 +MetaTest/__unnamed_task__/MinReturn -68.0418 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.34433 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2288e+07 +__unnamed_task__/AverageDiscountedReturn -28.2086 +__unnamed_task__/AverageReturn -50.9134 +__unnamed_task__/Iteration 255 +__unnamed_task__/MaxReturn -40.158 +__unnamed_task__/MinReturn -66.3933 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.88822 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 17:41:40 | [maml_trainer] epoch #256 | Sampling for adapation and meta-testing... +2025-04-08 17:45:33 | [maml_trainer] epoch #256 | Finished meta-testing... +2025-04-08 17:45:33 | [maml_trainer] epoch #256 | Saving snapshot... +2025-04-08 17:45:55 | [maml_trainer] epoch #256 | Saved +2025-04-08 17:45:55 | [maml_trainer] epoch #256 | Time 435998.98 s +2025-04-08 17:45:55 | [maml_trainer] epoch #256 | EpochTime 1652.32 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.285 +Average/AverageReturn -50.8003 +Average/Iteration 256 +Average/MaxReturn -39.7366 +Average/MinReturn -67.6818 +Average/NumEpisodes 120 +Average/StdReturn 5.52824 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81488 +GaussianMLPPolicy/KLAfter 0.00335379 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.50828e-05 +GaussianMLPPolicy/LossBefore -1.05699e-08 +GaussianMLPPolicy/dLoss 6.50723e-05 +Iteration 256 +MetaTest/Average/AverageDiscountedReturn -51.6202 +MetaTest/Average/AverageReturn -51.6202 +MetaTest/Average/Iteration 256 +MetaTest/Average/MaxReturn -44.2387 +MetaTest/Average/MinReturn -70.7647 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.09588 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6202 +MetaTest/__unnamed_task__/AverageReturn -51.6202 +MetaTest/__unnamed_task__/Iteration 256 +MetaTest/__unnamed_task__/MaxReturn -44.2387 +MetaTest/__unnamed_task__/MinReturn -70.7647 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.09588 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2336e+07 +__unnamed_task__/AverageDiscountedReturn -28.285 +__unnamed_task__/AverageReturn -50.8003 +__unnamed_task__/Iteration 256 +__unnamed_task__/MaxReturn -39.7366 +__unnamed_task__/MinReturn -67.6818 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.52824 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 18:09:04 | [maml_trainer] epoch #257 | Sampling for adapation and meta-testing... +2025-04-08 18:12:55 | [maml_trainer] epoch #257 | Finished meta-testing... +2025-04-08 18:12:55 | [maml_trainer] epoch #257 | Saving snapshot... +2025-04-08 18:13:17 | [maml_trainer] epoch #257 | Saved +2025-04-08 18:13:17 | [maml_trainer] epoch #257 | Time 437641.38 s +2025-04-08 18:13:17 | [maml_trainer] epoch #257 | EpochTime 1642.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1218 +Average/AverageReturn -50.2638 +Average/Iteration 257 +Average/MaxReturn -40.3363 +Average/MinReturn -64.8603 +Average/NumEpisodes 120 +Average/StdReturn 4.62723 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81479 +GaussianMLPPolicy/KLAfter 0.00318882 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000135177 +GaussianMLPPolicy/LossBefore -7.39098e-09 +GaussianMLPPolicy/dLoss 0.00013517 +Iteration 257 +MetaTest/Average/AverageDiscountedReturn -51.4133 +MetaTest/Average/AverageReturn -51.4133 +MetaTest/Average/Iteration 257 +MetaTest/Average/MaxReturn -42.9964 +MetaTest/Average/MinReturn -62.1273 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.12732 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.4133 +MetaTest/__unnamed_task__/AverageReturn -51.4133 +MetaTest/__unnamed_task__/Iteration 257 +MetaTest/__unnamed_task__/MaxReturn -42.9964 +MetaTest/__unnamed_task__/MinReturn -62.1273 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.12732 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2384e+07 +__unnamed_task__/AverageDiscountedReturn -28.1218 +__unnamed_task__/AverageReturn -50.2638 +__unnamed_task__/Iteration 257 +__unnamed_task__/MaxReturn -40.3363 +__unnamed_task__/MinReturn -64.8603 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.62723 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 18:36:30 | [maml_trainer] epoch #258 | Sampling for adapation and meta-testing... +2025-04-08 18:40:18 | [maml_trainer] epoch #258 | Finished meta-testing... +2025-04-08 18:40:18 | [maml_trainer] epoch #258 | Saving snapshot... +2025-04-08 18:40:39 | [maml_trainer] epoch #258 | Saved +2025-04-08 18:40:39 | [maml_trainer] epoch #258 | Time 439283.75 s +2025-04-08 18:40:39 | [maml_trainer] epoch #258 | EpochTime 1642.36 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3657 +Average/AverageReturn -50.6694 +Average/Iteration 258 +Average/MaxReturn -40.0581 +Average/MinReturn -67.4942 +Average/NumEpisodes 120 +Average/StdReturn 4.88521 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81517 +GaussianMLPPolicy/KLAfter 0.00363227 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.3953e-05 +GaussianMLPPolicy/LossBefore 6.35783e-10 +GaussianMLPPolicy/dLoss 3.39536e-05 +Iteration 258 +MetaTest/Average/AverageDiscountedReturn -51.6575 +MetaTest/Average/AverageReturn -51.6575 +MetaTest/Average/Iteration 258 +MetaTest/Average/MaxReturn -45.3498 +MetaTest/Average/MinReturn -67.2337 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.0089 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6575 +MetaTest/__unnamed_task__/AverageReturn -51.6575 +MetaTest/__unnamed_task__/Iteration 258 +MetaTest/__unnamed_task__/MaxReturn -45.3498 +MetaTest/__unnamed_task__/MinReturn -67.2337 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.0089 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2432e+07 +__unnamed_task__/AverageDiscountedReturn -28.3657 +__unnamed_task__/AverageReturn -50.6694 +__unnamed_task__/Iteration 258 +__unnamed_task__/MaxReturn -40.0581 +__unnamed_task__/MinReturn -67.4942 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.88521 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 19:03:31 | [maml_trainer] epoch #259 | Sampling for adapation and meta-testing... +2025-04-08 19:07:27 | [maml_trainer] epoch #259 | Finished meta-testing... +2025-04-08 19:07:27 | [maml_trainer] epoch #259 | Saving snapshot... +2025-04-08 19:07:49 | [maml_trainer] epoch #259 | Saved +2025-04-08 19:07:49 | [maml_trainer] epoch #259 | Time 440913.83 s +2025-04-08 19:07:49 | [maml_trainer] epoch #259 | EpochTime 1630.08 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2566 +Average/AverageReturn -49.8135 +Average/Iteration 259 +Average/MaxReturn -41.822 +Average/MinReturn -64.2976 +Average/NumEpisodes 120 +Average/StdReturn 4.27646 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81488 +GaussianMLPPolicy/KLAfter 0.00406883 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.75102e-05 +GaussianMLPPolicy/LossBefore -5.44389e-09 +GaussianMLPPolicy/dLoss 3.75048e-05 +Iteration 259 +MetaTest/Average/AverageDiscountedReturn -49.5193 +MetaTest/Average/AverageReturn -49.5193 +MetaTest/Average/Iteration 259 +MetaTest/Average/MaxReturn -43.1162 +MetaTest/Average/MinReturn -56.9616 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.75225 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5193 +MetaTest/__unnamed_task__/AverageReturn -49.5193 +MetaTest/__unnamed_task__/Iteration 259 +MetaTest/__unnamed_task__/MaxReturn -43.1162 +MetaTest/__unnamed_task__/MinReturn -56.9616 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.75225 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.248e+07 +__unnamed_task__/AverageDiscountedReturn -28.2566 +__unnamed_task__/AverageReturn -49.8135 +__unnamed_task__/Iteration 259 +__unnamed_task__/MaxReturn -41.822 +__unnamed_task__/MinReturn -64.2976 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.27646 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 19:31:06 | [maml_trainer] epoch #260 | Sampling for adapation and meta-testing... +2025-04-08 19:34:56 | [maml_trainer] epoch #260 | Finished meta-testing... +2025-04-08 19:34:56 | [maml_trainer] epoch #260 | Saving snapshot... +2025-04-08 19:35:18 | [maml_trainer] epoch #260 | Saved +2025-04-08 19:35:18 | [maml_trainer] epoch #260 | Time 442562.63 s +2025-04-08 19:35:18 | [maml_trainer] epoch #260 | EpochTime 1648.80 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3168 +Average/AverageReturn -50.3246 +Average/Iteration 260 +Average/MaxReturn -42.7115 +Average/MinReturn -62.9219 +Average/NumEpisodes 120 +Average/StdReturn 4.42751 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81442 +GaussianMLPPolicy/KLAfter 0.00546237 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.08459e-05 +GaussianMLPPolicy/LossBefore -6.27836e-09 +GaussianMLPPolicy/dLoss -8.08522e-05 +Iteration 260 +MetaTest/Average/AverageDiscountedReturn -49.9169 +MetaTest/Average/AverageReturn -49.9169 +MetaTest/Average/Iteration 260 +MetaTest/Average/MaxReturn -42.0238 +MetaTest/Average/MinReturn -61.4052 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.31004 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9169 +MetaTest/__unnamed_task__/AverageReturn -49.9169 +MetaTest/__unnamed_task__/Iteration 260 +MetaTest/__unnamed_task__/MaxReturn -42.0238 +MetaTest/__unnamed_task__/MinReturn -61.4052 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.31004 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2528e+07 +__unnamed_task__/AverageDiscountedReturn -28.3168 +__unnamed_task__/AverageReturn -50.3246 +__unnamed_task__/Iteration 260 +__unnamed_task__/MaxReturn -42.7115 +__unnamed_task__/MinReturn -62.9219 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.42751 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 19:58:15 | [maml_trainer] epoch #261 | Sampling for adapation and meta-testing... +2025-04-08 20:02:28 | [maml_trainer] epoch #261 | Finished meta-testing... +2025-04-08 20:02:28 | [maml_trainer] epoch #261 | Saving snapshot... +2025-04-08 20:02:50 | [maml_trainer] epoch #261 | Saved +2025-04-08 20:02:50 | [maml_trainer] epoch #261 | Time 444214.02 s +2025-04-08 20:02:50 | [maml_trainer] epoch #261 | EpochTime 1651.38 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5295 +Average/AverageReturn -50.6051 +Average/Iteration 261 +Average/MaxReturn -42.2108 +Average/MinReturn -67.4751 +Average/NumEpisodes 120 +Average/StdReturn 5.19148 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81442 +GaussianMLPPolicy/KLAfter 0.00561886 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000115875 +GaussianMLPPolicy/LossBefore 4.05312e-09 +GaussianMLPPolicy/dLoss -0.000115871 +Iteration 261 +MetaTest/Average/AverageDiscountedReturn -50.4645 +MetaTest/Average/AverageReturn -50.4645 +MetaTest/Average/Iteration 261 +MetaTest/Average/MaxReturn -41.8569 +MetaTest/Average/MinReturn -63.9215 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.35423 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4645 +MetaTest/__unnamed_task__/AverageReturn -50.4645 +MetaTest/__unnamed_task__/Iteration 261 +MetaTest/__unnamed_task__/MaxReturn -41.8569 +MetaTest/__unnamed_task__/MinReturn -63.9215 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.35423 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2576e+07 +__unnamed_task__/AverageDiscountedReturn -28.5295 +__unnamed_task__/AverageReturn -50.6051 +__unnamed_task__/Iteration 261 +__unnamed_task__/MaxReturn -42.2108 +__unnamed_task__/MinReturn -67.4751 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.19148 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 20:26:22 | [maml_trainer] epoch #262 | Sampling for adapation and meta-testing... +2025-04-08 20:30:15 | [maml_trainer] epoch #262 | Finished meta-testing... +2025-04-08 20:30:15 | [maml_trainer] epoch #262 | Saving snapshot... +2025-04-08 20:30:37 | [maml_trainer] epoch #262 | Saved +2025-04-08 20:30:37 | [maml_trainer] epoch #262 | Time 445881.20 s +2025-04-08 20:30:37 | [maml_trainer] epoch #262 | EpochTime 1667.18 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.6233 +Average/AverageReturn -50.6235 +Average/Iteration 262 +Average/MaxReturn -41.2696 +Average/MinReturn -66.6731 +Average/NumEpisodes 120 +Average/StdReturn 4.69136 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8137 +GaussianMLPPolicy/KLAfter 0.00399682 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000133093 +GaussianMLPPolicy/LossBefore 1.3113e-09 +GaussianMLPPolicy/dLoss 0.000133095 +Iteration 262 +MetaTest/Average/AverageDiscountedReturn -50.0577 +MetaTest/Average/AverageReturn -50.0577 +MetaTest/Average/Iteration 262 +MetaTest/Average/MaxReturn -42.8142 +MetaTest/Average/MinReturn -58.2205 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.17255 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0577 +MetaTest/__unnamed_task__/AverageReturn -50.0577 +MetaTest/__unnamed_task__/Iteration 262 +MetaTest/__unnamed_task__/MaxReturn -42.8142 +MetaTest/__unnamed_task__/MinReturn -58.2205 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.17255 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2624e+07 +__unnamed_task__/AverageDiscountedReturn -28.6233 +__unnamed_task__/AverageReturn -50.6235 +__unnamed_task__/Iteration 262 +__unnamed_task__/MaxReturn -41.2696 +__unnamed_task__/MinReturn -66.6731 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.69136 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 20:53:25 | [maml_trainer] epoch #263 | Sampling for adapation and meta-testing... +2025-04-08 20:57:18 | [maml_trainer] epoch #263 | Finished meta-testing... +2025-04-08 20:57:18 | [maml_trainer] epoch #263 | Saving snapshot... +2025-04-08 20:57:40 | [maml_trainer] epoch #263 | Saved +2025-04-08 20:57:40 | [maml_trainer] epoch #263 | Time 447504.91 s +2025-04-08 20:57:40 | [maml_trainer] epoch #263 | EpochTime 1623.70 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.9747 +Average/AverageReturn -50.955 +Average/Iteration 263 +Average/MaxReturn -43.0239 +Average/MinReturn -63.9216 +Average/NumEpisodes 120 +Average/StdReturn 4.16828 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81297 +GaussianMLPPolicy/KLAfter 0.00191469 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.17538e-05 +GaussianMLPPolicy/LossBefore -2.10603e-09 +GaussianMLPPolicy/dLoss 2.17517e-05 +Iteration 263 +MetaTest/Average/AverageDiscountedReturn -51.5658 +MetaTest/Average/AverageReturn -51.5658 +MetaTest/Average/Iteration 263 +MetaTest/Average/MaxReturn -44.5571 +MetaTest/Average/MinReturn -65.2779 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.17703 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.5658 +MetaTest/__unnamed_task__/AverageReturn -51.5658 +MetaTest/__unnamed_task__/Iteration 263 +MetaTest/__unnamed_task__/MaxReturn -44.5571 +MetaTest/__unnamed_task__/MinReturn -65.2779 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.17703 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2672e+07 +__unnamed_task__/AverageDiscountedReturn -28.9747 +__unnamed_task__/AverageReturn -50.955 +__unnamed_task__/Iteration 263 +__unnamed_task__/MaxReturn -43.0239 +__unnamed_task__/MinReturn -63.9216 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.16828 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 21:20:33 | [maml_trainer] epoch #264 | Sampling for adapation and meta-testing... +2025-04-08 21:24:21 | [maml_trainer] epoch #264 | Finished meta-testing... +2025-04-08 21:24:21 | [maml_trainer] epoch #264 | Saving snapshot... +2025-04-08 21:24:43 | [maml_trainer] epoch #264 | Saved +2025-04-08 21:24:43 | [maml_trainer] epoch #264 | Time 449127.26 s +2025-04-08 21:24:43 | [maml_trainer] epoch #264 | EpochTime 1622.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5979 +Average/AverageReturn -50.1359 +Average/Iteration 264 +Average/MaxReturn -42.5487 +Average/MinReturn -68.4266 +Average/NumEpisodes 120 +Average/StdReturn 4.70996 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81281 +GaussianMLPPolicy/KLAfter 0.00122223 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.53975e-05 +GaussianMLPPolicy/LossBefore -2.86102e-09 +GaussianMLPPolicy/dLoss -4.54003e-05 +Iteration 264 +MetaTest/Average/AverageDiscountedReturn -47.8891 +MetaTest/Average/AverageReturn -47.8891 +MetaTest/Average/Iteration 264 +MetaTest/Average/MaxReturn -40.8007 +MetaTest/Average/MinReturn -55.9981 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.15222 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8891 +MetaTest/__unnamed_task__/AverageReturn -47.8891 +MetaTest/__unnamed_task__/Iteration 264 +MetaTest/__unnamed_task__/MaxReturn -40.8007 +MetaTest/__unnamed_task__/MinReturn -55.9981 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.15222 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.272e+07 +__unnamed_task__/AverageDiscountedReturn -28.5979 +__unnamed_task__/AverageReturn -50.1359 +__unnamed_task__/Iteration 264 +__unnamed_task__/MaxReturn -42.5487 +__unnamed_task__/MinReturn -68.4266 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.70996 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 21:47:45 | [maml_trainer] epoch #265 | Sampling for adapation and meta-testing... +2025-04-08 21:51:39 | [maml_trainer] epoch #265 | Finished meta-testing... +2025-04-08 21:51:39 | [maml_trainer] epoch #265 | Saving snapshot... +2025-04-08 21:52:01 | [maml_trainer] epoch #265 | Saved +2025-04-08 21:52:01 | [maml_trainer] epoch #265 | Time 450765.21 s +2025-04-08 21:52:01 | [maml_trainer] epoch #265 | EpochTime 1637.94 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.7174 +Average/AverageReturn -50.3977 +Average/Iteration 265 +Average/MaxReturn -41.5667 +Average/MinReturn -69.3327 +Average/NumEpisodes 120 +Average/StdReturn 4.60206 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81243 +GaussianMLPPolicy/KLAfter 0.00170024 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.59944e-05 +GaussianMLPPolicy/LossBefore -1.89145e-08 +GaussianMLPPolicy/dLoss 5.59755e-05 +Iteration 265 +MetaTest/Average/AverageDiscountedReturn -48.1581 +MetaTest/Average/AverageReturn -48.1581 +MetaTest/Average/Iteration 265 +MetaTest/Average/MaxReturn -42.1243 +MetaTest/Average/MinReturn -73.304 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.48338 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1581 +MetaTest/__unnamed_task__/AverageReturn -48.1581 +MetaTest/__unnamed_task__/Iteration 265 +MetaTest/__unnamed_task__/MaxReturn -42.1243 +MetaTest/__unnamed_task__/MinReturn -73.304 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.48338 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2768e+07 +__unnamed_task__/AverageDiscountedReturn -28.7174 +__unnamed_task__/AverageReturn -50.3977 +__unnamed_task__/Iteration 265 +__unnamed_task__/MaxReturn -41.5667 +__unnamed_task__/MinReturn -69.3327 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.60206 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 22:15:02 | [maml_trainer] epoch #266 | Sampling for adapation and meta-testing... +2025-04-08 22:18:59 | [maml_trainer] epoch #266 | Finished meta-testing... +2025-04-08 22:18:59 | [maml_trainer] epoch #266 | Saving snapshot... +2025-04-08 22:19:21 | [maml_trainer] epoch #266 | Saved +2025-04-08 22:19:21 | [maml_trainer] epoch #266 | Time 452405.35 s +2025-04-08 22:19:21 | [maml_trainer] epoch #266 | EpochTime 1640.13 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4518 +Average/AverageReturn -50.0153 +Average/Iteration 266 +Average/MaxReturn -39.3597 +Average/MinReturn -71.7083 +Average/NumEpisodes 120 +Average/StdReturn 5.83994 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81314 +GaussianMLPPolicy/KLAfter 0.000977382 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.22264e-05 +GaussianMLPPolicy/LossBefore -2.82129e-09 +GaussianMLPPolicy/dLoss -3.22292e-05 +Iteration 266 +MetaTest/Average/AverageDiscountedReturn -50.0735 +MetaTest/Average/AverageReturn -50.0735 +MetaTest/Average/Iteration 266 +MetaTest/Average/MaxReturn -41.5898 +MetaTest/Average/MinReturn -61.9289 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.15052 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0735 +MetaTest/__unnamed_task__/AverageReturn -50.0735 +MetaTest/__unnamed_task__/Iteration 266 +MetaTest/__unnamed_task__/MaxReturn -41.5898 +MetaTest/__unnamed_task__/MinReturn -61.9289 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.15052 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2816e+07 +__unnamed_task__/AverageDiscountedReturn -28.4518 +__unnamed_task__/AverageReturn -50.0153 +__unnamed_task__/Iteration 266 +__unnamed_task__/MaxReturn -39.3597 +__unnamed_task__/MinReturn -71.7083 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.83994 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 22:42:47 | [maml_trainer] epoch #267 | Sampling for adapation and meta-testing... +2025-04-08 22:46:35 | [maml_trainer] epoch #267 | Finished meta-testing... +2025-04-08 22:46:35 | [maml_trainer] epoch #267 | Saving snapshot... +2025-04-08 22:46:57 | [maml_trainer] epoch #267 | Saved +2025-04-08 22:46:57 | [maml_trainer] epoch #267 | Time 454061.26 s +2025-04-08 22:46:57 | [maml_trainer] epoch #267 | EpochTime 1655.91 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.9627 +Average/AverageReturn -50.6296 +Average/Iteration 267 +Average/MaxReturn -43.4026 +Average/MinReturn -72.7114 +Average/NumEpisodes 120 +Average/StdReturn 5.05788 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81473 +GaussianMLPPolicy/KLAfter 0.00255857 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.94301e-06 +GaussianMLPPolicy/LossBefore 1.35104e-09 +GaussianMLPPolicy/dLoss 3.94436e-06 +Iteration 267 +MetaTest/Average/AverageDiscountedReturn -51.7591 +MetaTest/Average/AverageReturn -51.7591 +MetaTest/Average/Iteration 267 +MetaTest/Average/MaxReturn -45.287 +MetaTest/Average/MinReturn -67.4758 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.02884 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7591 +MetaTest/__unnamed_task__/AverageReturn -51.7591 +MetaTest/__unnamed_task__/Iteration 267 +MetaTest/__unnamed_task__/MaxReturn -45.287 +MetaTest/__unnamed_task__/MinReturn -67.4758 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.02884 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2864e+07 +__unnamed_task__/AverageDiscountedReturn -28.9627 +__unnamed_task__/AverageReturn -50.6296 +__unnamed_task__/Iteration 267 +__unnamed_task__/MaxReturn -43.4026 +__unnamed_task__/MinReturn -72.7114 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.05788 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 23:09:46 | [maml_trainer] epoch #268 | Sampling for adapation and meta-testing... +2025-04-08 23:13:36 | [maml_trainer] epoch #268 | Finished meta-testing... +2025-04-08 23:13:36 | [maml_trainer] epoch #268 | Saving snapshot... +2025-04-08 23:13:58 | [maml_trainer] epoch #268 | Saved +2025-04-08 23:13:58 | [maml_trainer] epoch #268 | Time 455682.31 s +2025-04-08 23:13:58 | [maml_trainer] epoch #268 | EpochTime 1621.04 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.7266 +Average/AverageReturn -50.4016 +Average/Iteration 268 +Average/MaxReturn -41.8801 +Average/MinReturn -73.5191 +Average/NumEpisodes 120 +Average/StdReturn 5.52221 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81628 +GaussianMLPPolicy/KLAfter 0.0025366 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.46283e-05 +GaussianMLPPolicy/LossBefore -1.8239e-08 +GaussianMLPPolicy/dLoss 2.46101e-05 +Iteration 268 +MetaTest/Average/AverageDiscountedReturn -49.7121 +MetaTest/Average/AverageReturn -49.7121 +MetaTest/Average/Iteration 268 +MetaTest/Average/MaxReturn -44.1861 +MetaTest/Average/MinReturn -70.9612 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.02533 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7121 +MetaTest/__unnamed_task__/AverageReturn -49.7121 +MetaTest/__unnamed_task__/Iteration 268 +MetaTest/__unnamed_task__/MaxReturn -44.1861 +MetaTest/__unnamed_task__/MinReturn -70.9612 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.02533 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.2912e+07 +__unnamed_task__/AverageDiscountedReturn -28.7266 +__unnamed_task__/AverageReturn -50.4016 +__unnamed_task__/Iteration 268 +__unnamed_task__/MaxReturn -41.8801 +__unnamed_task__/MinReturn -73.5191 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.52221 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-08 23:37:13 | [maml_trainer] epoch #269 | Sampling for adapation and meta-testing... +2025-04-08 23:41:11 | [maml_trainer] epoch #269 | Finished meta-testing... +2025-04-08 23:41:11 | [maml_trainer] epoch #269 | Saving snapshot... +2025-04-08 23:41:34 | [maml_trainer] epoch #269 | Saved +2025-04-08 23:41:34 | [maml_trainer] epoch #269 | Time 457338.64 s +2025-04-08 23:41:34 | [maml_trainer] epoch #269 | EpochTime 1656.32 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.5478 +Average/AverageReturn -50.1196 +Average/Iteration 269 +Average/MaxReturn -37.5275 +Average/MinReturn -100.751 +Average/NumEpisodes 120 +Average/StdReturn 6.78303 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81831 +GaussianMLPPolicy/KLAfter 0.00267246 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.82946e-05 +GaussianMLPPolicy/LossBefore 6.75519e-09 +GaussianMLPPolicy/dLoss 6.83014e-05 +Iteration 269 +MetaTest/Average/AverageDiscountedReturn -51.6289 +MetaTest/Average/AverageReturn -51.6289 +MetaTest/Average/Iteration 269 +MetaTest/Average/MaxReturn -42.5531 +MetaTest/Average/MinReturn -71.4088 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.19751 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6289 +MetaTest/__unnamed_task__/AverageReturn -51.6289 +MetaTest/__unnamed_task__/Iteration 269 +MetaTest/__unnamed_task__/MaxReturn -42.5531 +MetaTest/__unnamed_task__/MinReturn -71.4088 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.19751 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.296e+07 +__unnamed_task__/AverageDiscountedReturn -28.5478 +__unnamed_task__/AverageReturn -50.1196 +__unnamed_task__/Iteration 269 +__unnamed_task__/MaxReturn -37.5275 +__unnamed_task__/MinReturn -100.751 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.78303 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 00:06:06 | [maml_trainer] epoch #270 | Sampling for adapation and meta-testing... +2025-04-09 00:10:20 | [maml_trainer] epoch #270 | Finished meta-testing... +2025-04-09 00:10:20 | [maml_trainer] epoch #270 | Saving snapshot... +2025-04-09 00:10:45 | [maml_trainer] epoch #270 | Saved +2025-04-09 00:10:45 | [maml_trainer] epoch #270 | Time 459089.19 s +2025-04-09 00:10:45 | [maml_trainer] epoch #270 | EpochTime 1750.55 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2185 +Average/AverageReturn -49.2743 +Average/Iteration 270 +Average/MaxReturn -40.6208 +Average/MinReturn -64.9349 +Average/NumEpisodes 120 +Average/StdReturn 4.54364 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82019 +GaussianMLPPolicy/KLAfter 0.00277032 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.36063e-05 +GaussianMLPPolicy/LossBefore -1.13646e-08 +GaussianMLPPolicy/dLoss -1.36177e-05 +Iteration 270 +MetaTest/Average/AverageDiscountedReturn -54.4593 +MetaTest/Average/AverageReturn -54.4593 +MetaTest/Average/Iteration 270 +MetaTest/Average/MaxReturn -41.7308 +MetaTest/Average/MinReturn -98.8439 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.7289 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4593 +MetaTest/__unnamed_task__/AverageReturn -54.4593 +MetaTest/__unnamed_task__/Iteration 270 +MetaTest/__unnamed_task__/MaxReturn -41.7308 +MetaTest/__unnamed_task__/MinReturn -98.8439 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.7289 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3008e+07 +__unnamed_task__/AverageDiscountedReturn -28.2185 +__unnamed_task__/AverageReturn -49.2743 +__unnamed_task__/Iteration 270 +__unnamed_task__/MaxReturn -40.6208 +__unnamed_task__/MinReturn -64.9349 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.54364 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 00:34:29 | [maml_trainer] epoch #271 | Sampling for adapation and meta-testing... +2025-04-09 00:38:31 | [maml_trainer] epoch #271 | Finished meta-testing... +2025-04-09 00:38:31 | [maml_trainer] epoch #271 | Saving snapshot... +2025-04-09 00:38:54 | [maml_trainer] epoch #271 | Saved +2025-04-09 00:38:54 | [maml_trainer] epoch #271 | Time 460778.44 s +2025-04-09 00:38:54 | [maml_trainer] epoch #271 | EpochTime 1689.25 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0938 +Average/AverageReturn -49.407 +Average/Iteration 271 +Average/MaxReturn -39.8487 +Average/MinReturn -81.4531 +Average/NumEpisodes 120 +Average/StdReturn 5.37421 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82306 +GaussianMLPPolicy/KLAfter 0.00299575 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.51523e-05 +GaussianMLPPolicy/LossBefore 4.88758e-09 +GaussianMLPPolicy/dLoss -8.51474e-05 +Iteration 271 +MetaTest/Average/AverageDiscountedReturn -51.2202 +MetaTest/Average/AverageReturn -51.2202 +MetaTest/Average/Iteration 271 +MetaTest/Average/MaxReturn -41.3839 +MetaTest/Average/MinReturn -76.1015 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.68051 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2202 +MetaTest/__unnamed_task__/AverageReturn -51.2202 +MetaTest/__unnamed_task__/Iteration 271 +MetaTest/__unnamed_task__/MaxReturn -41.3839 +MetaTest/__unnamed_task__/MinReturn -76.1015 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.68051 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3056e+07 +__unnamed_task__/AverageDiscountedReturn -28.0938 +__unnamed_task__/AverageReturn -49.407 +__unnamed_task__/Iteration 271 +__unnamed_task__/MaxReturn -39.8487 +__unnamed_task__/MinReturn -81.4531 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.37421 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 01:03:34 | [maml_trainer] epoch #272 | Sampling for adapation and meta-testing... +2025-04-09 01:07:41 | [maml_trainer] epoch #272 | Finished meta-testing... +2025-04-09 01:07:41 | [maml_trainer] epoch #272 | Saving snapshot... +2025-04-09 01:08:05 | [maml_trainer] epoch #272 | Saved +2025-04-09 01:08:05 | [maml_trainer] epoch #272 | Time 462529.81 s +2025-04-09 01:08:05 | [maml_trainer] epoch #272 | EpochTime 1751.36 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.4613 +Average/AverageReturn -50.4857 +Average/Iteration 272 +Average/MaxReturn -40.6689 +Average/MinReturn -114.347 +Average/NumEpisodes 120 +Average/StdReturn 8.57467 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82628 +GaussianMLPPolicy/KLAfter 0.00256264 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.30399e-05 +GaussianMLPPolicy/LossBefore -8.0665e-09 +GaussianMLPPolicy/dLoss -5.3048e-05 +Iteration 272 +MetaTest/Average/AverageDiscountedReturn -48.8007 +MetaTest/Average/AverageReturn -48.8007 +MetaTest/Average/Iteration 272 +MetaTest/Average/MaxReturn -39.7879 +MetaTest/Average/MinReturn -63.2806 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.28178 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.8007 +MetaTest/__unnamed_task__/AverageReturn -48.8007 +MetaTest/__unnamed_task__/Iteration 272 +MetaTest/__unnamed_task__/MaxReturn -39.7879 +MetaTest/__unnamed_task__/MinReturn -63.2806 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.28178 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3104e+07 +__unnamed_task__/AverageDiscountedReturn -28.4613 +__unnamed_task__/AverageReturn -50.4857 +__unnamed_task__/Iteration 272 +__unnamed_task__/MaxReturn -40.6689 +__unnamed_task__/MinReturn -114.347 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.57467 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 01:32:35 | [maml_trainer] epoch #273 | Sampling for adapation and meta-testing... +2025-04-09 01:36:38 | [maml_trainer] epoch #273 | Finished meta-testing... +2025-04-09 01:36:38 | [maml_trainer] epoch #273 | Saving snapshot... +2025-04-09 01:37:02 | [maml_trainer] epoch #273 | Saved +2025-04-09 01:37:02 | [maml_trainer] epoch #273 | Time 464266.33 s +2025-04-09 01:37:02 | [maml_trainer] epoch #273 | EpochTime 1736.52 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.2669 +Average/AverageReturn -49.642 +Average/Iteration 273 +Average/MaxReturn -40.6593 +Average/MinReturn -67.3233 +Average/NumEpisodes 120 +Average/StdReturn 4.92566 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82942 +GaussianMLPPolicy/KLAfter 0.00292418 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.77065e-05 +GaussianMLPPolicy/LossBefore -1.06494e-08 +GaussianMLPPolicy/dLoss 1.76959e-05 +Iteration 273 +MetaTest/Average/AverageDiscountedReturn -47.4458 +MetaTest/Average/AverageReturn -47.4458 +MetaTest/Average/Iteration 273 +MetaTest/Average/MaxReturn -41.3833 +MetaTest/Average/MinReturn -56.0826 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.13223 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4458 +MetaTest/__unnamed_task__/AverageReturn -47.4458 +MetaTest/__unnamed_task__/Iteration 273 +MetaTest/__unnamed_task__/MaxReturn -41.3833 +MetaTest/__unnamed_task__/MinReturn -56.0826 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.13223 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3152e+07 +__unnamed_task__/AverageDiscountedReturn -28.2669 +__unnamed_task__/AverageReturn -49.642 +__unnamed_task__/Iteration 273 +__unnamed_task__/MaxReturn -40.6593 +__unnamed_task__/MinReturn -67.3233 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.92566 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 02:01:46 | [maml_trainer] epoch #274 | Sampling for adapation and meta-testing... +2025-04-09 02:05:53 | [maml_trainer] epoch #274 | Finished meta-testing... +2025-04-09 02:05:53 | [maml_trainer] epoch #274 | Saving snapshot... +2025-04-09 02:06:17 | [maml_trainer] epoch #274 | Saved +2025-04-09 02:06:17 | [maml_trainer] epoch #274 | Time 466020.99 s +2025-04-09 02:06:17 | [maml_trainer] epoch #274 | EpochTime 1754.66 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9853 +Average/AverageReturn -49.4955 +Average/Iteration 274 +Average/MaxReturn -39.0308 +Average/MinReturn -76.9814 +Average/NumEpisodes 120 +Average/StdReturn 6.02259 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83177 +GaussianMLPPolicy/KLAfter 0.0019978 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.44412e-05 +GaussianMLPPolicy/LossBefore 3.77496e-09 +GaussianMLPPolicy/dLoss 5.4445e-05 +Iteration 274 +MetaTest/Average/AverageDiscountedReturn -49.8404 +MetaTest/Average/AverageReturn -49.8404 +MetaTest/Average/Iteration 274 +MetaTest/Average/MaxReturn -41.9535 +MetaTest/Average/MinReturn -67.8896 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.4591 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8404 +MetaTest/__unnamed_task__/AverageReturn -49.8404 +MetaTest/__unnamed_task__/Iteration 274 +MetaTest/__unnamed_task__/MaxReturn -41.9535 +MetaTest/__unnamed_task__/MinReturn -67.8896 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.4591 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.32e+07 +__unnamed_task__/AverageDiscountedReturn -27.9853 +__unnamed_task__/AverageReturn -49.4955 +__unnamed_task__/Iteration 274 +__unnamed_task__/MaxReturn -39.0308 +__unnamed_task__/MinReturn -76.9814 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.02259 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 02:31:01 | [maml_trainer] epoch #275 | Sampling for adapation and meta-testing... +2025-04-09 02:35:09 | [maml_trainer] epoch #275 | Finished meta-testing... +2025-04-09 02:35:09 | [maml_trainer] epoch #275 | Saving snapshot... +2025-04-09 02:35:33 | [maml_trainer] epoch #275 | Saved +2025-04-09 02:35:33 | [maml_trainer] epoch #275 | Time 467777.45 s +2025-04-09 02:35:33 | [maml_trainer] epoch #275 | EpochTime 1756.46 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6669 +Average/AverageReturn -48.741 +Average/Iteration 275 +Average/MaxReturn -40.6618 +Average/MinReturn -67.3038 +Average/NumEpisodes 120 +Average/StdReturn 4.74014 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83372 +GaussianMLPPolicy/KLAfter 0.00197046 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.0001426 +GaussianMLPPolicy/LossBefore -3.73522e-09 +GaussianMLPPolicy/dLoss 0.000142597 +Iteration 275 +MetaTest/Average/AverageDiscountedReturn -48.7942 +MetaTest/Average/AverageReturn -48.7942 +MetaTest/Average/Iteration 275 +MetaTest/Average/MaxReturn -41.8104 +MetaTest/Average/MinReturn -55.8639 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.36093 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7942 +MetaTest/__unnamed_task__/AverageReturn -48.7942 +MetaTest/__unnamed_task__/Iteration 275 +MetaTest/__unnamed_task__/MaxReturn -41.8104 +MetaTest/__unnamed_task__/MinReturn -55.8639 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.36093 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3248e+07 +__unnamed_task__/AverageDiscountedReturn -27.6669 +__unnamed_task__/AverageReturn -48.741 +__unnamed_task__/Iteration 275 +__unnamed_task__/MaxReturn -40.6618 +__unnamed_task__/MinReturn -67.3038 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.74014 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 03:00:07 | [maml_trainer] epoch #276 | Sampling for adapation and meta-testing... +2025-04-09 03:04:16 | [maml_trainer] epoch #276 | Finished meta-testing... +2025-04-09 03:04:16 | [maml_trainer] epoch #276 | Saving snapshot... +2025-04-09 03:04:39 | [maml_trainer] epoch #276 | Saved +2025-04-09 03:04:39 | [maml_trainer] epoch #276 | Time 469523.90 s +2025-04-09 03:04:39 | [maml_trainer] epoch #276 | EpochTime 1746.44 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.3744 +Average/AverageReturn -48.1684 +Average/Iteration 276 +Average/MaxReturn -39.8668 +Average/MinReturn -66.3583 +Average/NumEpisodes 120 +Average/StdReturn 4.51664 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83575 +GaussianMLPPolicy/KLAfter 0.00262957 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000212673 +GaussianMLPPolicy/LossBefore 4.13259e-09 +GaussianMLPPolicy/dLoss -0.000212669 +Iteration 276 +MetaTest/Average/AverageDiscountedReturn -49.1689 +MetaTest/Average/AverageReturn -49.1689 +MetaTest/Average/Iteration 276 +MetaTest/Average/MaxReturn -21.3024 +MetaTest/Average/MinReturn -66.3441 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.58445 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1689 +MetaTest/__unnamed_task__/AverageReturn -49.1689 +MetaTest/__unnamed_task__/Iteration 276 +MetaTest/__unnamed_task__/MaxReturn -21.3024 +MetaTest/__unnamed_task__/MinReturn -66.3441 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.58445 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3296e+07 +__unnamed_task__/AverageDiscountedReturn -27.3744 +__unnamed_task__/AverageReturn -48.1684 +__unnamed_task__/Iteration 276 +__unnamed_task__/MaxReturn -39.8668 +__unnamed_task__/MinReturn -66.3583 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.51664 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 03:29:22 | [maml_trainer] epoch #277 | Sampling for adapation and meta-testing... +2025-04-09 03:33:30 | [maml_trainer] epoch #277 | Finished meta-testing... +2025-04-09 03:33:30 | [maml_trainer] epoch #277 | Saving snapshot... +2025-04-09 03:33:54 | [maml_trainer] epoch #277 | Saved +2025-04-09 03:33:54 | [maml_trainer] epoch #277 | Time 471278.76 s +2025-04-09 03:33:54 | [maml_trainer] epoch #277 | EpochTime 1754.86 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6337 +Average/AverageReturn -49.0864 +Average/Iteration 277 +Average/MaxReturn -38.5068 +Average/MinReturn -64.8973 +Average/NumEpisodes 120 +Average/StdReturn 5.54763 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83725 +GaussianMLPPolicy/KLAfter 0.00331177 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000101932 +GaussianMLPPolicy/LossBefore -7.35124e-09 +GaussianMLPPolicy/dLoss -0.00010194 +Iteration 277 +MetaTest/Average/AverageDiscountedReturn -52.3787 +MetaTest/Average/AverageReturn -52.3787 +MetaTest/Average/Iteration 277 +MetaTest/Average/MaxReturn -41.566 +MetaTest/Average/MinReturn -92.0921 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.6209 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3787 +MetaTest/__unnamed_task__/AverageReturn -52.3787 +MetaTest/__unnamed_task__/Iteration 277 +MetaTest/__unnamed_task__/MaxReturn -41.566 +MetaTest/__unnamed_task__/MinReturn -92.0921 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.6209 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3344e+07 +__unnamed_task__/AverageDiscountedReturn -27.6337 +__unnamed_task__/AverageReturn -49.0864 +__unnamed_task__/Iteration 277 +__unnamed_task__/MaxReturn -38.5068 +__unnamed_task__/MinReturn -64.8973 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.54763 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 03:58:42 | [maml_trainer] epoch #278 | Sampling for adapation and meta-testing... +2025-04-09 04:02:51 | [maml_trainer] epoch #278 | Finished meta-testing... +2025-04-09 04:02:51 | [maml_trainer] epoch #278 | Saving snapshot... +2025-04-09 04:03:15 | [maml_trainer] epoch #278 | Saved +2025-04-09 04:03:15 | [maml_trainer] epoch #278 | Time 473039.05 s +2025-04-09 04:03:15 | [maml_trainer] epoch #278 | EpochTime 1760.29 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.424 +Average/AverageReturn -49.2935 +Average/Iteration 278 +Average/MaxReturn -38.9248 +Average/MinReturn -114.021 +Average/NumEpisodes 120 +Average/StdReturn 8.67271 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83877 +GaussianMLPPolicy/KLAfter 0.00242004 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.63e-07 +GaussianMLPPolicy/LossBefore -1.95503e-08 +GaussianMLPPolicy/dLoss 1.43449e-07 +Iteration 278 +MetaTest/Average/AverageDiscountedReturn -54.5271 +MetaTest/Average/AverageReturn -54.5271 +MetaTest/Average/Iteration 278 +MetaTest/Average/MaxReturn -42.1816 +MetaTest/Average/MinReturn -98.578 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.6559 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.5271 +MetaTest/__unnamed_task__/AverageReturn -54.5271 +MetaTest/__unnamed_task__/Iteration 278 +MetaTest/__unnamed_task__/MaxReturn -42.1816 +MetaTest/__unnamed_task__/MinReturn -98.578 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.6559 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3392e+07 +__unnamed_task__/AverageDiscountedReturn -27.424 +__unnamed_task__/AverageReturn -49.2935 +__unnamed_task__/Iteration 278 +__unnamed_task__/MaxReturn -38.9248 +__unnamed_task__/MinReturn -114.021 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.67271 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 04:28:01 | [maml_trainer] epoch #279 | Sampling for adapation and meta-testing... +2025-04-09 04:32:09 | [maml_trainer] epoch #279 | Finished meta-testing... +2025-04-09 04:32:09 | [maml_trainer] epoch #279 | Saving snapshot... +2025-04-09 04:32:33 | [maml_trainer] epoch #279 | Saved +2025-04-09 04:32:33 | [maml_trainer] epoch #279 | Time 474797.86 s +2025-04-09 04:32:33 | [maml_trainer] epoch #279 | EpochTime 1758.81 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.3237 +Average/AverageReturn -48.7237 +Average/Iteration 279 +Average/MaxReturn 152.609 +Average/MinReturn -170.53 +Average/NumEpisodes 120 +Average/StdReturn 30.6231 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83968 +GaussianMLPPolicy/KLAfter 0.00297534 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.06895e-05 +GaussianMLPPolicy/LossBefore -1.81794e-09 +GaussianMLPPolicy/dLoss 4.06877e-05 +Iteration 279 +MetaTest/Average/AverageDiscountedReturn -61.6429 +MetaTest/Average/AverageReturn -61.6429 +MetaTest/Average/Iteration 279 +MetaTest/Average/MaxReturn -44.1243 +MetaTest/Average/MinReturn -153.438 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.3329 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -61.6429 +MetaTest/__unnamed_task__/AverageReturn -61.6429 +MetaTest/__unnamed_task__/Iteration 279 +MetaTest/__unnamed_task__/MaxReturn -44.1243 +MetaTest/__unnamed_task__/MinReturn -153.438 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.3329 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.344e+07 +__unnamed_task__/AverageDiscountedReturn -27.3237 +__unnamed_task__/AverageReturn -48.7237 +__unnamed_task__/Iteration 279 +__unnamed_task__/MaxReturn 152.609 +__unnamed_task__/MinReturn -170.53 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 30.6231 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 04:57:13 | [maml_trainer] epoch #280 | Sampling for adapation and meta-testing... +2025-04-09 05:01:21 | [maml_trainer] epoch #280 | Finished meta-testing... +2025-04-09 05:01:21 | [maml_trainer] epoch #280 | Saving snapshot... +2025-04-09 05:01:45 | [maml_trainer] epoch #280 | Saved +2025-04-09 05:01:45 | [maml_trainer] epoch #280 | Time 476549.33 s +2025-04-09 05:01:45 | [maml_trainer] epoch #280 | EpochTime 1751.46 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.4006 +Average/AverageReturn -50.4869 +Average/Iteration 280 +Average/MaxReturn -32.6479 +Average/MinReturn -172.711 +Average/NumEpisodes 120 +Average/StdReturn 16.5795 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84033 +GaussianMLPPolicy/KLAfter 0.00205126 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.45333e-06 +GaussianMLPPolicy/LossBefore 6.77506e-09 +GaussianMLPPolicy/dLoss 6.46011e-06 +Iteration 280 +MetaTest/Average/AverageDiscountedReturn -49.959 +MetaTest/Average/AverageReturn -49.959 +MetaTest/Average/Iteration 280 +MetaTest/Average/MaxReturn -40.0369 +MetaTest/Average/MinReturn -69.5839 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.77003 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.959 +MetaTest/__unnamed_task__/AverageReturn -49.959 +MetaTest/__unnamed_task__/Iteration 280 +MetaTest/__unnamed_task__/MaxReturn -40.0369 +MetaTest/__unnamed_task__/MinReturn -69.5839 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.77003 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3488e+07 +__unnamed_task__/AverageDiscountedReturn -27.4006 +__unnamed_task__/AverageReturn -50.4869 +__unnamed_task__/Iteration 280 +__unnamed_task__/MaxReturn -32.6479 +__unnamed_task__/MinReturn -172.711 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.5795 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 05:26:46 | [maml_trainer] epoch #281 | Sampling for adapation and meta-testing... +2025-04-09 05:30:54 | [maml_trainer] epoch #281 | Finished meta-testing... +2025-04-09 05:30:54 | [maml_trainer] epoch #281 | Saving snapshot... +2025-04-09 05:31:18 | [maml_trainer] epoch #281 | Saved +2025-04-09 05:31:18 | [maml_trainer] epoch #281 | Time 478322.06 s +2025-04-09 05:31:18 | [maml_trainer] epoch #281 | EpochTime 1772.72 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.6919 +Average/AverageReturn -52.208 +Average/Iteration 281 +Average/MaxReturn -37.6851 +Average/MinReturn -139.59 +Average/NumEpisodes 120 +Average/StdReturn 14.8945 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.842 +GaussianMLPPolicy/KLAfter 0.000762792 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.20295e-05 +GaussianMLPPolicy/LossBefore 1.15236e-09 +GaussianMLPPolicy/dLoss -1.20283e-05 +Iteration 281 +MetaTest/Average/AverageDiscountedReturn -49.5727 +MetaTest/Average/AverageReturn -49.5727 +MetaTest/Average/Iteration 281 +MetaTest/Average/MaxReturn -39.4861 +MetaTest/Average/MinReturn -78.1038 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.29383 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5727 +MetaTest/__unnamed_task__/AverageReturn -49.5727 +MetaTest/__unnamed_task__/Iteration 281 +MetaTest/__unnamed_task__/MaxReturn -39.4861 +MetaTest/__unnamed_task__/MinReturn -78.1038 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.29383 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3536e+07 +__unnamed_task__/AverageDiscountedReturn -27.6919 +__unnamed_task__/AverageReturn -52.208 +__unnamed_task__/Iteration 281 +__unnamed_task__/MaxReturn -37.6851 +__unnamed_task__/MinReturn -139.59 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.8945 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 05:56:03 | [maml_trainer] epoch #282 | Sampling for adapation and meta-testing... +2025-04-09 06:00:11 | [maml_trainer] epoch #282 | Finished meta-testing... +2025-04-09 06:00:11 | [maml_trainer] epoch #282 | Saving snapshot... +2025-04-09 06:00:35 | [maml_trainer] epoch #282 | Saved +2025-04-09 06:00:35 | [maml_trainer] epoch #282 | Time 480079.03 s +2025-04-09 06:00:35 | [maml_trainer] epoch #282 | EpochTime 1756.97 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.0888 +Average/AverageReturn -53.07 +Average/Iteration 282 +Average/MaxReturn -39.8601 +Average/MinReturn -161.478 +Average/NumEpisodes 120 +Average/StdReturn 16.0315 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84298 +GaussianMLPPolicy/KLAfter 0.00115119 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.47356e-05 +GaussianMLPPolicy/LossBefore -3.17891e-10 +GaussianMLPPolicy/dLoss 2.47353e-05 +Iteration 282 +MetaTest/Average/AverageDiscountedReturn -48.9273 +MetaTest/Average/AverageReturn -48.9273 +MetaTest/Average/Iteration 282 +MetaTest/Average/MaxReturn -41.2956 +MetaTest/Average/MinReturn -71.7271 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.75402 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9273 +MetaTest/__unnamed_task__/AverageReturn -48.9273 +MetaTest/__unnamed_task__/Iteration 282 +MetaTest/__unnamed_task__/MaxReturn -41.2956 +MetaTest/__unnamed_task__/MinReturn -71.7271 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.75402 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3584e+07 +__unnamed_task__/AverageDiscountedReturn -28.0888 +__unnamed_task__/AverageReturn -53.07 +__unnamed_task__/Iteration 282 +__unnamed_task__/MaxReturn -39.8601 +__unnamed_task__/MinReturn -161.478 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.0315 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 06:25:18 | [maml_trainer] epoch #283 | Sampling for adapation and meta-testing... +2025-04-09 06:29:23 | [maml_trainer] epoch #283 | Finished meta-testing... +2025-04-09 06:29:23 | [maml_trainer] epoch #283 | Saving snapshot... +2025-04-09 06:29:46 | [maml_trainer] epoch #283 | Saved +2025-04-09 06:29:46 | [maml_trainer] epoch #283 | Time 481830.92 s +2025-04-09 06:29:46 | [maml_trainer] epoch #283 | EpochTime 1751.88 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2197 +Average/AverageReturn -48.7057 +Average/Iteration 283 +Average/MaxReturn -37.8917 +Average/MinReturn -93.0199 +Average/NumEpisodes 120 +Average/StdReturn 6.47548 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84334 +GaussianMLPPolicy/KLAfter 0.000902342 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.005e-05 +GaussianMLPPolicy/LossBefore -7.3115e-09 +GaussianMLPPolicy/dLoss -6.00573e-05 +Iteration 283 +MetaTest/Average/AverageDiscountedReturn -53.994 +MetaTest/Average/AverageReturn -53.994 +MetaTest/Average/Iteration 283 +MetaTest/Average/MaxReturn -39.8354 +MetaTest/Average/MinReturn -164.762 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 26.0334 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.994 +MetaTest/__unnamed_task__/AverageReturn -53.994 +MetaTest/__unnamed_task__/Iteration 283 +MetaTest/__unnamed_task__/MaxReturn -39.8354 +MetaTest/__unnamed_task__/MinReturn -164.762 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 26.0334 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3632e+07 +__unnamed_task__/AverageDiscountedReturn -27.2197 +__unnamed_task__/AverageReturn -48.7057 +__unnamed_task__/Iteration 283 +__unnamed_task__/MaxReturn -37.8917 +__unnamed_task__/MinReturn -93.0199 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.47548 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 06:54:36 | [maml_trainer] epoch #284 | Sampling for adapation and meta-testing... +2025-04-09 06:58:44 | [maml_trainer] epoch #284 | Finished meta-testing... +2025-04-09 06:58:44 | [maml_trainer] epoch #284 | Saving snapshot... +2025-04-09 06:59:08 | [maml_trainer] epoch #284 | Saved +2025-04-09 06:59:08 | [maml_trainer] epoch #284 | Time 483592.12 s +2025-04-09 06:59:08 | [maml_trainer] epoch #284 | EpochTime 1761.20 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2562 +Average/AverageReturn -49.3392 +Average/Iteration 284 +Average/MaxReturn -40.6804 +Average/MinReturn -125.351 +Average/NumEpisodes 120 +Average/StdReturn 9.22924 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84422 +GaussianMLPPolicy/KLAfter 0.00117181 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.2106e-05 +GaussianMLPPolicy/LossBefore -2.38419e-09 +GaussianMLPPolicy/dLoss 1.21036e-05 +Iteration 284 +MetaTest/Average/AverageDiscountedReturn -54.9511 +MetaTest/Average/AverageReturn -54.9511 +MetaTest/Average/Iteration 284 +MetaTest/Average/MaxReturn -41.8783 +MetaTest/Average/MinReturn -157.794 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 24.0959 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.9511 +MetaTest/__unnamed_task__/AverageReturn -54.9511 +MetaTest/__unnamed_task__/Iteration 284 +MetaTest/__unnamed_task__/MaxReturn -41.8783 +MetaTest/__unnamed_task__/MinReturn -157.794 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 24.0959 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.368e+07 +__unnamed_task__/AverageDiscountedReturn -27.2562 +__unnamed_task__/AverageReturn -49.3392 +__unnamed_task__/Iteration 284 +__unnamed_task__/MaxReturn -40.6804 +__unnamed_task__/MinReturn -125.351 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.22924 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 07:23:58 | [maml_trainer] epoch #285 | Sampling for adapation and meta-testing... +2025-04-09 07:28:08 | [maml_trainer] epoch #285 | Finished meta-testing... +2025-04-09 07:28:08 | [maml_trainer] epoch #285 | Saving snapshot... +2025-04-09 07:28:32 | [maml_trainer] epoch #285 | Saved +2025-04-09 07:28:32 | [maml_trainer] epoch #285 | Time 485356.61 s +2025-04-09 07:28:32 | [maml_trainer] epoch #285 | EpochTime 1764.49 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.656 +Average/AverageReturn -50.1084 +Average/Iteration 285 +Average/MaxReturn -39.9202 +Average/MinReturn -93.6819 +Average/NumEpisodes 120 +Average/StdReturn 7.15493 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84486 +GaussianMLPPolicy/KLAfter 0.000480827 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.10755e-05 +GaussianMLPPolicy/LossBefore -5.16574e-09 +GaussianMLPPolicy/dLoss 2.10704e-05 +Iteration 285 +MetaTest/Average/AverageDiscountedReturn -49.1741 +MetaTest/Average/AverageReturn -49.1741 +MetaTest/Average/Iteration 285 +MetaTest/Average/MaxReturn -41.9384 +MetaTest/Average/MinReturn -66.4693 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.19832 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1741 +MetaTest/__unnamed_task__/AverageReturn -49.1741 +MetaTest/__unnamed_task__/Iteration 285 +MetaTest/__unnamed_task__/MaxReturn -41.9384 +MetaTest/__unnamed_task__/MinReturn -66.4693 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.19832 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3728e+07 +__unnamed_task__/AverageDiscountedReturn -27.656 +__unnamed_task__/AverageReturn -50.1084 +__unnamed_task__/Iteration 285 +__unnamed_task__/MaxReturn -39.9202 +__unnamed_task__/MinReturn -93.6819 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.15493 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 07:53:23 | [maml_trainer] epoch #286 | Sampling for adapation and meta-testing... +2025-04-09 07:57:31 | [maml_trainer] epoch #286 | Finished meta-testing... +2025-04-09 07:57:31 | [maml_trainer] epoch #286 | Saving snapshot... +2025-04-09 07:57:55 | [maml_trainer] epoch #286 | Saved +2025-04-09 07:57:55 | [maml_trainer] epoch #286 | Time 487119.04 s +2025-04-09 07:57:55 | [maml_trainer] epoch #286 | EpochTime 1762.43 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.4658 +Average/AverageReturn -49.0478 +Average/Iteration 286 +Average/MaxReturn -38.5596 +Average/MinReturn -84.1677 +Average/NumEpisodes 120 +Average/StdReturn 6.23412 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84592 +GaussianMLPPolicy/KLAfter 0.0018605 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.02779e-07 +GaussianMLPPolicy/LossBefore 4.88758e-09 +GaussianMLPPolicy/dLoss -6.97891e-07 +Iteration 286 +MetaTest/Average/AverageDiscountedReturn -53.4291 +MetaTest/Average/AverageReturn -53.4291 +MetaTest/Average/Iteration 286 +MetaTest/Average/MaxReturn -41.6058 +MetaTest/Average/MinReturn -146.921 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 22.0642 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4291 +MetaTest/__unnamed_task__/AverageReturn -53.4291 +MetaTest/__unnamed_task__/Iteration 286 +MetaTest/__unnamed_task__/MaxReturn -41.6058 +MetaTest/__unnamed_task__/MinReturn -146.921 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 22.0642 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3776e+07 +__unnamed_task__/AverageDiscountedReturn -27.4658 +__unnamed_task__/AverageReturn -49.0478 +__unnamed_task__/Iteration 286 +__unnamed_task__/MaxReturn -38.5596 +__unnamed_task__/MinReturn -84.1677 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.23412 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 08:22:43 | [maml_trainer] epoch #287 | Sampling for adapation and meta-testing... +2025-04-09 08:26:53 | [maml_trainer] epoch #287 | Finished meta-testing... +2025-04-09 08:26:53 | [maml_trainer] epoch #287 | Saving snapshot... +2025-04-09 08:27:17 | [maml_trainer] epoch #287 | Saved +2025-04-09 08:27:17 | [maml_trainer] epoch #287 | Time 488881.42 s +2025-04-09 08:27:17 | [maml_trainer] epoch #287 | EpochTime 1762.37 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.4829 +Average/AverageReturn -49.7213 +Average/Iteration 287 +Average/MaxReturn -39.285 +Average/MinReturn -88.0941 +Average/NumEpisodes 120 +Average/StdReturn 6.92731 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84657 +GaussianMLPPolicy/KLAfter 0.00157238 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.53728e-05 +GaussianMLPPolicy/LossBefore 4.56969e-09 +GaussianMLPPolicy/dLoss 6.53774e-05 +Iteration 287 +MetaTest/Average/AverageDiscountedReturn -31.3637 +MetaTest/Average/AverageReturn -31.3637 +MetaTest/Average/Iteration 287 +MetaTest/Average/MaxReturn 313.418 +MetaTest/Average/MinReturn -69.6087 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 79.3604 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -31.3637 +MetaTest/__unnamed_task__/AverageReturn -31.3637 +MetaTest/__unnamed_task__/Iteration 287 +MetaTest/__unnamed_task__/MaxReturn 313.418 +MetaTest/__unnamed_task__/MinReturn -69.6087 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 79.3604 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3824e+07 +__unnamed_task__/AverageDiscountedReturn -27.4829 +__unnamed_task__/AverageReturn -49.7213 +__unnamed_task__/Iteration 287 +__unnamed_task__/MaxReturn -39.285 +__unnamed_task__/MinReturn -88.0941 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.92731 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 08:52:01 | [maml_trainer] epoch #288 | Sampling for adapation and meta-testing... +2025-04-09 08:56:10 | [maml_trainer] epoch #288 | Finished meta-testing... +2025-04-09 08:56:10 | [maml_trainer] epoch #288 | Saving snapshot... +2025-04-09 08:56:33 | [maml_trainer] epoch #288 | Saved +2025-04-09 08:56:33 | [maml_trainer] epoch #288 | Time 490637.84 s +2025-04-09 08:56:33 | [maml_trainer] epoch #288 | EpochTime 1756.42 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2883 +Average/AverageReturn -48.6802 +Average/Iteration 288 +Average/MaxReturn -38.8967 +Average/MinReturn -70.9829 +Average/NumEpisodes 120 +Average/StdReturn 5.1151 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84763 +GaussianMLPPolicy/KLAfter 0.000705939 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.97368e-05 +GaussianMLPPolicy/LossBefore -4.41074e-09 +GaussianMLPPolicy/dLoss 1.97324e-05 +Iteration 288 +MetaTest/Average/AverageDiscountedReturn -49.3488 +MetaTest/Average/AverageReturn -49.3488 +MetaTest/Average/Iteration 288 +MetaTest/Average/MaxReturn -41.2212 +MetaTest/Average/MinReturn -64.1248 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.67222 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3488 +MetaTest/__unnamed_task__/AverageReturn -49.3488 +MetaTest/__unnamed_task__/Iteration 288 +MetaTest/__unnamed_task__/MaxReturn -41.2212 +MetaTest/__unnamed_task__/MinReturn -64.1248 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.67222 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3872e+07 +__unnamed_task__/AverageDiscountedReturn -27.2883 +__unnamed_task__/AverageReturn -48.6802 +__unnamed_task__/Iteration 288 +__unnamed_task__/MaxReturn -38.8967 +__unnamed_task__/MinReturn -70.9829 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.1151 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 09:21:13 | [maml_trainer] epoch #289 | Sampling for adapation and meta-testing... +2025-04-09 09:25:21 | [maml_trainer] epoch #289 | Finished meta-testing... +2025-04-09 09:25:21 | [maml_trainer] epoch #289 | Saving snapshot... +2025-04-09 09:25:45 | [maml_trainer] epoch #289 | Saved +2025-04-09 09:25:45 | [maml_trainer] epoch #289 | Time 492389.94 s +2025-04-09 09:25:45 | [maml_trainer] epoch #289 | EpochTime 1752.10 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.349 +Average/AverageReturn -48.4652 +Average/Iteration 289 +Average/MaxReturn -39.1301 +Average/MinReturn -69.9492 +Average/NumEpisodes 120 +Average/StdReturn 4.94534 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84709 +GaussianMLPPolicy/KLAfter 0.000723787 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.35118e-05 +GaussianMLPPolicy/LossBefore 7.23203e-09 +GaussianMLPPolicy/dLoss -2.35046e-05 +Iteration 289 +MetaTest/Average/AverageDiscountedReturn -48.9327 +MetaTest/Average/AverageReturn -48.9327 +MetaTest/Average/Iteration 289 +MetaTest/Average/MaxReturn -41.9294 +MetaTest/Average/MinReturn -62.9215 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.04952 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9327 +MetaTest/__unnamed_task__/AverageReturn -48.9327 +MetaTest/__unnamed_task__/Iteration 289 +MetaTest/__unnamed_task__/MaxReturn -41.9294 +MetaTest/__unnamed_task__/MinReturn -62.9215 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.04952 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.392e+07 +__unnamed_task__/AverageDiscountedReturn -27.349 +__unnamed_task__/AverageReturn -48.4652 +__unnamed_task__/Iteration 289 +__unnamed_task__/MaxReturn -39.1301 +__unnamed_task__/MinReturn -69.9492 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.94534 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 09:50:41 | [maml_trainer] epoch #290 | Sampling for adapation and meta-testing... +2025-04-09 09:54:45 | [maml_trainer] epoch #290 | Finished meta-testing... +2025-04-09 09:54:45 | [maml_trainer] epoch #290 | Saving snapshot... +2025-04-09 09:55:09 | [maml_trainer] epoch #290 | Saved +2025-04-09 09:55:09 | [maml_trainer] epoch #290 | Time 494153.09 s +2025-04-09 09:55:09 | [maml_trainer] epoch #290 | EpochTime 1763.15 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.5587 +Average/AverageReturn -48.9164 +Average/Iteration 290 +Average/MaxReturn -39.458 +Average/MinReturn -75.9641 +Average/NumEpisodes 120 +Average/StdReturn 5.34426 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84744 +GaussianMLPPolicy/KLAfter 0.0008764 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.21229e-05 +GaussianMLPPolicy/LossBefore -5.44389e-09 +GaussianMLPPolicy/dLoss 2.21175e-05 +Iteration 290 +MetaTest/Average/AverageDiscountedReturn -49.0783 +MetaTest/Average/AverageReturn -49.0783 +MetaTest/Average/Iteration 290 +MetaTest/Average/MaxReturn -41.4701 +MetaTest/Average/MinReturn -58.0019 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.81865 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.0783 +MetaTest/__unnamed_task__/AverageReturn -49.0783 +MetaTest/__unnamed_task__/Iteration 290 +MetaTest/__unnamed_task__/MaxReturn -41.4701 +MetaTest/__unnamed_task__/MinReturn -58.0019 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.81865 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.3968e+07 +__unnamed_task__/AverageDiscountedReturn -27.5587 +__unnamed_task__/AverageReturn -48.9164 +__unnamed_task__/Iteration 290 +__unnamed_task__/MaxReturn -39.458 +__unnamed_task__/MinReturn -75.9641 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.34426 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 10:20:01 | [maml_trainer] epoch #291 | Sampling for adapation and meta-testing... +2025-04-09 10:24:10 | [maml_trainer] epoch #291 | Finished meta-testing... +2025-04-09 10:24:10 | [maml_trainer] epoch #291 | Saving snapshot... +2025-04-09 10:24:32 | [maml_trainer] epoch #291 | Saved +2025-04-09 10:24:32 | [maml_trainer] epoch #291 | Time 495916.84 s +2025-04-09 10:24:32 | [maml_trainer] epoch #291 | EpochTime 1763.74 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.127 +Average/AverageReturn -48.4691 +Average/Iteration 291 +Average/MaxReturn -39.5616 +Average/MinReturn -94.3705 +Average/NumEpisodes 120 +Average/StdReturn 6.14701 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84723 +GaussianMLPPolicy/KLAfter 0.00115406 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.14162e-06 +GaussianMLPPolicy/LossBefore -6.71546e-09 +GaussianMLPPolicy/dLoss 5.1349e-06 +Iteration 291 +MetaTest/Average/AverageDiscountedReturn -50.2765 +MetaTest/Average/AverageReturn -50.2765 +MetaTest/Average/Iteration 291 +MetaTest/Average/MaxReturn -43.9955 +MetaTest/Average/MinReturn -61.29 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.62471 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2765 +MetaTest/__unnamed_task__/AverageReturn -50.2765 +MetaTest/__unnamed_task__/Iteration 291 +MetaTest/__unnamed_task__/MaxReturn -43.9955 +MetaTest/__unnamed_task__/MinReturn -61.29 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.62471 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4016e+07 +__unnamed_task__/AverageDiscountedReturn -27.127 +__unnamed_task__/AverageReturn -48.4691 +__unnamed_task__/Iteration 291 +__unnamed_task__/MaxReturn -39.5616 +__unnamed_task__/MinReturn -94.3705 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.14701 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 10:49:11 | [maml_trainer] epoch #292 | Sampling for adapation and meta-testing... +2025-04-09 10:53:20 | [maml_trainer] epoch #292 | Finished meta-testing... +2025-04-09 10:53:20 | [maml_trainer] epoch #292 | Saving snapshot... +2025-04-09 10:53:44 | [maml_trainer] epoch #292 | Saved +2025-04-09 10:53:44 | [maml_trainer] epoch #292 | Time 497668.85 s +2025-04-09 10:53:44 | [maml_trainer] epoch #292 | EpochTime 1752.01 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.4992 +Average/AverageReturn -49.0204 +Average/Iteration 292 +Average/MaxReturn -41.2151 +Average/MinReturn -65.4878 +Average/NumEpisodes 120 +Average/StdReturn 5.31237 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84703 +GaussianMLPPolicy/KLAfter 0.00102341 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.04341e-05 +GaussianMLPPolicy/LossBefore -6.07967e-09 +GaussianMLPPolicy/dLoss -3.04401e-05 +Iteration 292 +MetaTest/Average/AverageDiscountedReturn -49.039 +MetaTest/Average/AverageReturn -49.039 +MetaTest/Average/Iteration 292 +MetaTest/Average/MaxReturn -40.0913 +MetaTest/Average/MinReturn -65.3579 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.47538 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.039 +MetaTest/__unnamed_task__/AverageReturn -49.039 +MetaTest/__unnamed_task__/Iteration 292 +MetaTest/__unnamed_task__/MaxReturn -40.0913 +MetaTest/__unnamed_task__/MinReturn -65.3579 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.47538 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4064e+07 +__unnamed_task__/AverageDiscountedReturn -27.4992 +__unnamed_task__/AverageReturn -49.0204 +__unnamed_task__/Iteration 292 +__unnamed_task__/MaxReturn -41.2151 +__unnamed_task__/MinReturn -65.4878 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.31237 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 11:18:15 | [maml_trainer] epoch #293 | Sampling for adapation and meta-testing... +2025-04-09 11:22:21 | [maml_trainer] epoch #293 | Finished meta-testing... +2025-04-09 11:22:21 | [maml_trainer] epoch #293 | Saving snapshot... +2025-04-09 11:22:44 | [maml_trainer] epoch #293 | Saved +2025-04-09 11:22:44 | [maml_trainer] epoch #293 | Time 499408.61 s +2025-04-09 11:22:44 | [maml_trainer] epoch #293 | EpochTime 1739.75 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2754 +Average/AverageReturn -49.5307 +Average/Iteration 293 +Average/MaxReturn -40.7706 +Average/MinReturn -172.508 +Average/NumEpisodes 120 +Average/StdReturn 12.2557 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84702 +GaussianMLPPolicy/KLAfter 0.000815953 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.02136e-05 +GaussianMLPPolicy/LossBefore -5.72205e-09 +GaussianMLPPolicy/dLoss 4.02079e-05 +Iteration 293 +MetaTest/Average/AverageDiscountedReturn -51.2676 +MetaTest/Average/AverageReturn -51.2676 +MetaTest/Average/Iteration 293 +MetaTest/Average/MaxReturn -43.5892 +MetaTest/Average/MinReturn -64.7348 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.44633 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2676 +MetaTest/__unnamed_task__/AverageReturn -51.2676 +MetaTest/__unnamed_task__/Iteration 293 +MetaTest/__unnamed_task__/MaxReturn -43.5892 +MetaTest/__unnamed_task__/MinReturn -64.7348 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.44633 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4112e+07 +__unnamed_task__/AverageDiscountedReturn -27.2754 +__unnamed_task__/AverageReturn -49.5307 +__unnamed_task__/Iteration 293 +__unnamed_task__/MaxReturn -40.7706 +__unnamed_task__/MinReturn -172.508 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.2557 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 11:47:40 | [maml_trainer] epoch #294 | Sampling for adapation and meta-testing... +2025-04-09 11:51:55 | [maml_trainer] epoch #294 | Finished meta-testing... +2025-04-09 11:51:55 | [maml_trainer] epoch #294 | Saving snapshot... +2025-04-09 11:52:18 | [maml_trainer] epoch #294 | Saved +2025-04-09 11:52:18 | [maml_trainer] epoch #294 | Time 501181.97 s +2025-04-09 11:52:18 | [maml_trainer] epoch #294 | EpochTime 1773.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6121 +Average/AverageReturn -49.8579 +Average/Iteration 294 +Average/MaxReturn -40.3695 +Average/MinReturn -69.3989 +Average/NumEpisodes 120 +Average/StdReturn 5.90292 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84722 +GaussianMLPPolicy/KLAfter 0.00116165 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.94859e-05 +GaussianMLPPolicy/LossBefore -2.04643e-08 +GaussianMLPPolicy/dLoss -3.95064e-05 +Iteration 294 +MetaTest/Average/AverageDiscountedReturn -48.2488 +MetaTest/Average/AverageReturn -48.2488 +MetaTest/Average/Iteration 294 +MetaTest/Average/MaxReturn -41.839 +MetaTest/Average/MinReturn -61.1988 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.64504 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2488 +MetaTest/__unnamed_task__/AverageReturn -48.2488 +MetaTest/__unnamed_task__/Iteration 294 +MetaTest/__unnamed_task__/MaxReturn -41.839 +MetaTest/__unnamed_task__/MinReturn -61.1988 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.64504 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.416e+07 +__unnamed_task__/AverageDiscountedReturn -27.6121 +__unnamed_task__/AverageReturn -49.8579 +__unnamed_task__/Iteration 294 +__unnamed_task__/MaxReturn -40.3695 +__unnamed_task__/MinReturn -69.3989 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.90292 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 12:16:45 | [maml_trainer] epoch #295 | Sampling for adapation and meta-testing... +2025-04-09 12:20:50 | [maml_trainer] epoch #295 | Finished meta-testing... +2025-04-09 12:20:50 | [maml_trainer] epoch #295 | Saving snapshot... +2025-04-09 12:21:12 | [maml_trainer] epoch #295 | Saved +2025-04-09 12:21:12 | [maml_trainer] epoch #295 | Time 502916.01 s +2025-04-09 12:21:12 | [maml_trainer] epoch #295 | EpochTime 1734.04 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.5042 +Average/AverageReturn -50.5934 +Average/Iteration 295 +Average/MaxReturn -39.3843 +Average/MinReturn -126.272 +Average/NumEpisodes 120 +Average/StdReturn 9.44996 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8471 +GaussianMLPPolicy/KLAfter 0.00175551 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.86884e-06 +GaussianMLPPolicy/LossBefore -7.94729e-10 +GaussianMLPPolicy/dLoss -1.86964e-06 +Iteration 295 +MetaTest/Average/AverageDiscountedReturn -45.4909 +MetaTest/Average/AverageReturn -45.4909 +MetaTest/Average/Iteration 295 +MetaTest/Average/MaxReturn -40.1536 +MetaTest/Average/MinReturn -50.5906 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.92968 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.4909 +MetaTest/__unnamed_task__/AverageReturn -45.4909 +MetaTest/__unnamed_task__/Iteration 295 +MetaTest/__unnamed_task__/MaxReturn -40.1536 +MetaTest/__unnamed_task__/MinReturn -50.5906 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.92968 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4208e+07 +__unnamed_task__/AverageDiscountedReturn -27.5042 +__unnamed_task__/AverageReturn -50.5934 +__unnamed_task__/Iteration 295 +__unnamed_task__/MaxReturn -39.3843 +__unnamed_task__/MinReturn -126.272 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.44996 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 12:45:55 | [maml_trainer] epoch #296 | Sampling for adapation and meta-testing... +2025-04-09 12:50:08 | [maml_trainer] epoch #296 | Finished meta-testing... +2025-04-09 12:50:08 | [maml_trainer] epoch #296 | Saving snapshot... +2025-04-09 12:50:31 | [maml_trainer] epoch #296 | Saved +2025-04-09 12:50:31 | [maml_trainer] epoch #296 | Time 504675.35 s +2025-04-09 12:50:31 | [maml_trainer] epoch #296 | EpochTime 1759.33 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2516 +Average/AverageReturn -49.6713 +Average/Iteration 296 +Average/MaxReturn -39.2384 +Average/MinReturn -113.654 +Average/NumEpisodes 120 +Average/StdReturn 8.27973 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84663 +GaussianMLPPolicy/KLAfter 0.00328026 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.76853e-05 +GaussianMLPPolicy/LossBefore 1.53383e-08 +GaussianMLPPolicy/dLoss 8.77007e-05 +Iteration 296 +MetaTest/Average/AverageDiscountedReturn -51.7015 +MetaTest/Average/AverageReturn -51.7015 +MetaTest/Average/Iteration 296 +MetaTest/Average/MaxReturn -42.783 +MetaTest/Average/MinReturn -72.6487 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.14165 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.7015 +MetaTest/__unnamed_task__/AverageReturn -51.7015 +MetaTest/__unnamed_task__/Iteration 296 +MetaTest/__unnamed_task__/MaxReturn -42.783 +MetaTest/__unnamed_task__/MinReturn -72.6487 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.14165 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4256e+07 +__unnamed_task__/AverageDiscountedReturn -27.2516 +__unnamed_task__/AverageReturn -49.6713 +__unnamed_task__/Iteration 296 +__unnamed_task__/MaxReturn -39.2384 +__unnamed_task__/MinReturn -113.654 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.27973 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 13:15:03 | [maml_trainer] epoch #297 | Sampling for adapation and meta-testing... +2025-04-09 13:19:01 | [maml_trainer] epoch #297 | Finished meta-testing... +2025-04-09 13:19:01 | [maml_trainer] epoch #297 | Saving snapshot... +2025-04-09 13:19:21 | [maml_trainer] epoch #297 | Saved +2025-04-09 13:19:21 | [maml_trainer] epoch #297 | Time 506405.93 s +2025-04-09 13:19:21 | [maml_trainer] epoch #297 | EpochTime 1730.58 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6231 +Average/AverageReturn -50.3713 +Average/Iteration 297 +Average/MaxReturn -39.8247 +Average/MinReturn -72.188 +Average/NumEpisodes 120 +Average/StdReturn 6.66166 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84547 +GaussianMLPPolicy/KLAfter 0.00188862 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.7503e-05 +GaussianMLPPolicy/LossBefore 1.51793e-08 +GaussianMLPPolicy/dLoss -4.74879e-05 +Iteration 297 +MetaTest/Average/AverageDiscountedReturn -48.2738 +MetaTest/Average/AverageReturn -48.2738 +MetaTest/Average/Iteration 297 +MetaTest/Average/MaxReturn -38.3258 +MetaTest/Average/MinReturn -72.5338 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.90826 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2738 +MetaTest/__unnamed_task__/AverageReturn -48.2738 +MetaTest/__unnamed_task__/Iteration 297 +MetaTest/__unnamed_task__/MaxReturn -38.3258 +MetaTest/__unnamed_task__/MinReturn -72.5338 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.90826 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4304e+07 +__unnamed_task__/AverageDiscountedReturn -27.6231 +__unnamed_task__/AverageReturn -50.3713 +__unnamed_task__/Iteration 297 +__unnamed_task__/MaxReturn -39.8247 +__unnamed_task__/MinReturn -72.188 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.66166 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 13:43:19 | [maml_trainer] epoch #298 | Sampling for adapation and meta-testing... +2025-04-09 13:47:10 | [maml_trainer] epoch #298 | Finished meta-testing... +2025-04-09 13:47:10 | [maml_trainer] epoch #298 | Saving snapshot... +2025-04-09 13:47:31 | [maml_trainer] epoch #298 | Saved +2025-04-09 13:47:31 | [maml_trainer] epoch #298 | Time 508095.52 s +2025-04-09 13:47:31 | [maml_trainer] epoch #298 | EpochTime 1689.58 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.295 +Average/AverageReturn -49.1143 +Average/Iteration 298 +Average/MaxReturn -39.9629 +Average/MinReturn -74.0346 +Average/NumEpisodes 120 +Average/StdReturn 6.09844 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84549 +GaussianMLPPolicy/KLAfter 0.00115314 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.32421e-05 +GaussianMLPPolicy/LossBefore 1.42256e-08 +GaussianMLPPolicy/dLoss 4.32563e-05 +Iteration 298 +MetaTest/Average/AverageDiscountedReturn -47.6657 +MetaTest/Average/AverageReturn -47.6657 +MetaTest/Average/Iteration 298 +MetaTest/Average/MaxReturn -38.097 +MetaTest/Average/MinReturn -59.6643 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.54947 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.6657 +MetaTest/__unnamed_task__/AverageReturn -47.6657 +MetaTest/__unnamed_task__/Iteration 298 +MetaTest/__unnamed_task__/MaxReturn -38.097 +MetaTest/__unnamed_task__/MinReturn -59.6643 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.54947 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4352e+07 +__unnamed_task__/AverageDiscountedReturn -27.295 +__unnamed_task__/AverageReturn -49.1143 +__unnamed_task__/Iteration 298 +__unnamed_task__/MaxReturn -39.9629 +__unnamed_task__/MinReturn -74.0346 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.09844 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 14:10:59 | [maml_trainer] epoch #299 | Sampling for adapation and meta-testing... +2025-04-09 14:14:52 | [maml_trainer] epoch #299 | Finished meta-testing... +2025-04-09 14:14:52 | [maml_trainer] epoch #299 | Saving snapshot... +2025-04-09 14:15:13 | [maml_trainer] epoch #299 | Saved +2025-04-09 14:15:13 | [maml_trainer] epoch #299 | Time 509757.53 s +2025-04-09 14:15:13 | [maml_trainer] epoch #299 | EpochTime 1662.01 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6847 +Average/AverageReturn -50.2265 +Average/Iteration 299 +Average/MaxReturn -39.3224 +Average/MinReturn -70.4965 +Average/NumEpisodes 120 +Average/StdReturn 5.96782 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84422 +GaussianMLPPolicy/KLAfter 0.00156841 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.24486e-06 +GaussianMLPPolicy/LossBefore 5.84126e-09 +GaussianMLPPolicy/dLoss 1.2507e-06 +Iteration 299 +MetaTest/Average/AverageDiscountedReturn -50.6979 +MetaTest/Average/AverageReturn -50.6979 +MetaTest/Average/Iteration 299 +MetaTest/Average/MaxReturn -43.5031 +MetaTest/Average/MinReturn -62.9053 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.63054 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6979 +MetaTest/__unnamed_task__/AverageReturn -50.6979 +MetaTest/__unnamed_task__/Iteration 299 +MetaTest/__unnamed_task__/MaxReturn -43.5031 +MetaTest/__unnamed_task__/MinReturn -62.9053 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.63054 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.44e+07 +__unnamed_task__/AverageDiscountedReturn -27.6847 +__unnamed_task__/AverageReturn -50.2265 +__unnamed_task__/Iteration 299 +__unnamed_task__/MaxReturn -39.3224 +__unnamed_task__/MinReturn -70.4965 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.96782 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 14:38:36 | [maml_trainer] epoch #300 | Sampling for adapation and meta-testing... +2025-04-09 14:42:31 | [maml_trainer] epoch #300 | Finished meta-testing... +2025-04-09 14:42:31 | [maml_trainer] epoch #300 | Saving snapshot... +2025-04-09 14:42:52 | [maml_trainer] epoch #300 | Saved +2025-04-09 14:42:52 | [maml_trainer] epoch #300 | Time 511416.01 s +2025-04-09 14:42:52 | [maml_trainer] epoch #300 | EpochTime 1658.48 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.3556 +Average/AverageReturn -49.2573 +Average/Iteration 300 +Average/MaxReturn -38.3259 +Average/MinReturn -75.2044 +Average/NumEpisodes 120 +Average/StdReturn 5.81219 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84355 +GaussianMLPPolicy/KLAfter 0.00123328 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.68387e-05 +GaussianMLPPolicy/LossBefore 1.61727e-08 +GaussianMLPPolicy/dLoss 2.68548e-05 +Iteration 300 +MetaTest/Average/AverageDiscountedReturn -48.9058 +MetaTest/Average/AverageReturn -48.9058 +MetaTest/Average/Iteration 300 +MetaTest/Average/MaxReturn -41.6639 +MetaTest/Average/MinReturn -65.6491 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.89462 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9058 +MetaTest/__unnamed_task__/AverageReturn -48.9058 +MetaTest/__unnamed_task__/Iteration 300 +MetaTest/__unnamed_task__/MaxReturn -41.6639 +MetaTest/__unnamed_task__/MinReturn -65.6491 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.89462 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4448e+07 +__unnamed_task__/AverageDiscountedReturn -27.3556 +__unnamed_task__/AverageReturn -49.2573 +__unnamed_task__/Iteration 300 +__unnamed_task__/MaxReturn -38.3259 +__unnamed_task__/MinReturn -75.2044 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.81219 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 15:06:12 | [maml_trainer] epoch #301 | Sampling for adapation and meta-testing... +2025-04-09 15:10:06 | [maml_trainer] epoch #301 | Finished meta-testing... +2025-04-09 15:10:06 | [maml_trainer] epoch #301 | Saving snapshot... +2025-04-09 15:10:27 | [maml_trainer] epoch #301 | Saved +2025-04-09 15:10:27 | [maml_trainer] epoch #301 | Time 513071.30 s +2025-04-09 15:10:27 | [maml_trainer] epoch #301 | EpochTime 1655.29 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.4661 +Average/AverageReturn -49.6923 +Average/Iteration 301 +Average/MaxReturn -40.3277 +Average/MinReturn -84.606 +Average/NumEpisodes 120 +Average/StdReturn 7.71979 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84343 +GaussianMLPPolicy/KLAfter 0.00176131 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.45148e-05 +GaussianMLPPolicy/LossBefore -4.84784e-09 +GaussianMLPPolicy/dLoss -5.45196e-05 +Iteration 301 +MetaTest/Average/AverageDiscountedReturn -47.4397 +MetaTest/Average/AverageReturn -47.4397 +MetaTest/Average/Iteration 301 +MetaTest/Average/MaxReturn -39.6059 +MetaTest/Average/MinReturn -61.9059 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.78599 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4397 +MetaTest/__unnamed_task__/AverageReturn -47.4397 +MetaTest/__unnamed_task__/Iteration 301 +MetaTest/__unnamed_task__/MaxReturn -39.6059 +MetaTest/__unnamed_task__/MinReturn -61.9059 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.78599 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4496e+07 +__unnamed_task__/AverageDiscountedReturn -27.4661 +__unnamed_task__/AverageReturn -49.6923 +__unnamed_task__/Iteration 301 +__unnamed_task__/MaxReturn -40.3277 +__unnamed_task__/MinReturn -84.606 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.71979 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 15:33:54 | [maml_trainer] epoch #302 | Sampling for adapation and meta-testing... +2025-04-09 15:37:48 | [maml_trainer] epoch #302 | Finished meta-testing... +2025-04-09 15:37:48 | [maml_trainer] epoch #302 | Saving snapshot... +2025-04-09 15:38:10 | [maml_trainer] epoch #302 | Saved +2025-04-09 15:38:10 | [maml_trainer] epoch #302 | Time 514734.50 s +2025-04-09 15:38:10 | [maml_trainer] epoch #302 | EpochTime 1663.19 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.3138 +Average/AverageReturn -49.4382 +Average/Iteration 302 +Average/MaxReturn -40.6835 +Average/MinReturn -112.395 +Average/NumEpisodes 120 +Average/StdReturn 8.37214 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.84023 +GaussianMLPPolicy/KLAfter 0.00384613 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.33737e-05 +GaussianMLPPolicy/LossBefore 5.08626e-09 +GaussianMLPPolicy/dLoss 2.33788e-05 +Iteration 302 +MetaTest/Average/AverageDiscountedReturn -49.6437 +MetaTest/Average/AverageReturn -49.6437 +MetaTest/Average/Iteration 302 +MetaTest/Average/MaxReturn -42.3981 +MetaTest/Average/MinReturn -58.9913 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.01655 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6437 +MetaTest/__unnamed_task__/AverageReturn -49.6437 +MetaTest/__unnamed_task__/Iteration 302 +MetaTest/__unnamed_task__/MaxReturn -42.3981 +MetaTest/__unnamed_task__/MinReturn -58.9913 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.01655 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4544e+07 +__unnamed_task__/AverageDiscountedReturn -27.3138 +__unnamed_task__/AverageReturn -49.4382 +__unnamed_task__/Iteration 302 +__unnamed_task__/MaxReturn -40.6835 +__unnamed_task__/MinReturn -112.395 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.37214 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 16:01:40 | [maml_trainer] epoch #303 | Sampling for adapation and meta-testing... +2025-04-09 16:05:39 | [maml_trainer] epoch #303 | Finished meta-testing... +2025-04-09 16:05:39 | [maml_trainer] epoch #303 | Saving snapshot... +2025-04-09 16:06:00 | [maml_trainer] epoch #303 | Saved +2025-04-09 16:06:00 | [maml_trainer] epoch #303 | Time 516404.49 s +2025-04-09 16:06:00 | [maml_trainer] epoch #303 | EpochTime 1669.99 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.6435 +Average/AverageReturn -50.0157 +Average/Iteration 303 +Average/MaxReturn -35.2054 +Average/MinReturn -172.974 +Average/NumEpisodes 120 +Average/StdReturn 12.5192 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83751 +GaussianMLPPolicy/KLAfter 0.00561018 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.88774e-05 +GaussianMLPPolicy/LossBefore 8.0665e-09 +GaussianMLPPolicy/dLoss 1.88855e-05 +Iteration 303 +MetaTest/Average/AverageDiscountedReturn -49.103 +MetaTest/Average/AverageReturn -49.103 +MetaTest/Average/Iteration 303 +MetaTest/Average/MaxReturn -43.2332 +MetaTest/Average/MinReturn -56.9792 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.70519 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.103 +MetaTest/__unnamed_task__/AverageReturn -49.103 +MetaTest/__unnamed_task__/Iteration 303 +MetaTest/__unnamed_task__/MaxReturn -43.2332 +MetaTest/__unnamed_task__/MinReturn -56.9792 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.70519 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4592e+07 +__unnamed_task__/AverageDiscountedReturn -27.6435 +__unnamed_task__/AverageReturn -50.0157 +__unnamed_task__/Iteration 303 +__unnamed_task__/MaxReturn -35.2054 +__unnamed_task__/MinReturn -172.974 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.5192 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 16:29:24 | [maml_trainer] epoch #304 | Sampling for adapation and meta-testing... +2025-04-09 16:33:16 | [maml_trainer] epoch #304 | Finished meta-testing... +2025-04-09 16:33:16 | [maml_trainer] epoch #304 | Saving snapshot... +2025-04-09 16:33:37 | [maml_trainer] epoch #304 | Saved +2025-04-09 16:33:37 | [maml_trainer] epoch #304 | Time 518061.86 s +2025-04-09 16:33:37 | [maml_trainer] epoch #304 | EpochTime 1657.37 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.4735 +Average/AverageReturn -50.0475 +Average/Iteration 304 +Average/MaxReturn -37.9322 +Average/MinReturn -148.979 +Average/NumEpisodes 120 +Average/StdReturn 11.5478 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8335 +GaussianMLPPolicy/KLAfter 0.00588801 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.58181e-05 +GaussianMLPPolicy/LossBefore -1.37488e-08 +GaussianMLPPolicy/dLoss -3.58318e-05 +Iteration 304 +MetaTest/Average/AverageDiscountedReturn -48.1274 +MetaTest/Average/AverageReturn -48.1274 +MetaTest/Average/Iteration 304 +MetaTest/Average/MaxReturn -40.96 +MetaTest/Average/MinReturn -64.5883 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.01947 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1274 +MetaTest/__unnamed_task__/AverageReturn -48.1274 +MetaTest/__unnamed_task__/Iteration 304 +MetaTest/__unnamed_task__/MaxReturn -40.96 +MetaTest/__unnamed_task__/MinReturn -64.5883 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.01947 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.464e+07 +__unnamed_task__/AverageDiscountedReturn -27.4735 +__unnamed_task__/AverageReturn -50.0475 +__unnamed_task__/Iteration 304 +__unnamed_task__/MaxReturn -37.9322 +__unnamed_task__/MinReturn -148.979 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.5478 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 16:56:45 | [maml_trainer] epoch #305 | Sampling for adapation and meta-testing... +2025-04-09 17:00:37 | [maml_trainer] epoch #305 | Finished meta-testing... +2025-04-09 17:00:37 | [maml_trainer] epoch #305 | Saving snapshot... +2025-04-09 17:00:57 | [maml_trainer] epoch #305 | Saved +2025-04-09 17:00:57 | [maml_trainer] epoch #305 | Time 519701.67 s +2025-04-09 17:00:57 | [maml_trainer] epoch #305 | EpochTime 1639.80 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.541 +Average/AverageReturn -49.2156 +Average/Iteration 305 +Average/MaxReturn -38.6683 +Average/MinReturn -93.3203 +Average/NumEpisodes 120 +Average/StdReturn 6.71797 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.83035 +GaussianMLPPolicy/KLAfter 0.00349265 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.34735e-05 +GaussianMLPPolicy/LossBefore -4.13259e-09 +GaussianMLPPolicy/dLoss -3.34776e-05 +Iteration 305 +MetaTest/Average/AverageDiscountedReturn -49.327 +MetaTest/Average/AverageReturn -49.327 +MetaTest/Average/Iteration 305 +MetaTest/Average/MaxReturn -42.9457 +MetaTest/Average/MinReturn -61.3962 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.78991 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.327 +MetaTest/__unnamed_task__/AverageReturn -49.327 +MetaTest/__unnamed_task__/Iteration 305 +MetaTest/__unnamed_task__/MaxReturn -42.9457 +MetaTest/__unnamed_task__/MinReturn -61.3962 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.78991 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4688e+07 +__unnamed_task__/AverageDiscountedReturn -27.541 +__unnamed_task__/AverageReturn -49.2156 +__unnamed_task__/Iteration 305 +__unnamed_task__/MaxReturn -38.6683 +__unnamed_task__/MinReturn -93.3203 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.71797 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 17:24:11 | [maml_trainer] epoch #306 | Sampling for adapation and meta-testing... +2025-04-09 17:28:05 | [maml_trainer] epoch #306 | Finished meta-testing... +2025-04-09 17:28:05 | [maml_trainer] epoch #306 | Saving snapshot... +2025-04-09 17:28:26 | [maml_trainer] epoch #306 | Saved +2025-04-09 17:28:26 | [maml_trainer] epoch #306 | Time 521350.41 s +2025-04-09 17:28:26 | [maml_trainer] epoch #306 | EpochTime 1648.74 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.4808 +Average/AverageReturn -48.6592 +Average/Iteration 306 +Average/MaxReturn -37.898 +Average/MinReturn -61.8893 +Average/NumEpisodes 120 +Average/StdReturn 4.6246 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82694 +GaussianMLPPolicy/KLAfter 0.00278436 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.0318e-05 +GaussianMLPPolicy/LossBefore -7.23203e-09 +GaussianMLPPolicy/dLoss 3.03108e-05 +Iteration 306 +MetaTest/Average/AverageDiscountedReturn -51.3009 +MetaTest/Average/AverageReturn -51.3009 +MetaTest/Average/Iteration 306 +MetaTest/Average/MaxReturn -43.872 +MetaTest/Average/MinReturn -78.0513 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.23548 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3009 +MetaTest/__unnamed_task__/AverageReturn -51.3009 +MetaTest/__unnamed_task__/Iteration 306 +MetaTest/__unnamed_task__/MaxReturn -43.872 +MetaTest/__unnamed_task__/MinReturn -78.0513 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.23548 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4736e+07 +__unnamed_task__/AverageDiscountedReturn -27.4808 +__unnamed_task__/AverageReturn -48.6592 +__unnamed_task__/Iteration 306 +__unnamed_task__/MaxReturn -37.898 +__unnamed_task__/MinReturn -61.8893 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.6246 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 17:51:52 | [maml_trainer] epoch #307 | Sampling for adapation and meta-testing... +2025-04-09 17:55:40 | [maml_trainer] epoch #307 | Finished meta-testing... +2025-04-09 17:55:40 | [maml_trainer] epoch #307 | Saving snapshot... +2025-04-09 17:56:02 | [maml_trainer] epoch #307 | Saved +2025-04-09 17:56:02 | [maml_trainer] epoch #307 | Time 523006.25 s +2025-04-09 17:56:02 | [maml_trainer] epoch #307 | EpochTime 1655.83 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.909 +Average/AverageReturn -49.5095 +Average/Iteration 307 +Average/MaxReturn -39.5722 +Average/MinReturn -118.274 +Average/NumEpisodes 120 +Average/StdReturn 7.87854 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82512 +GaussianMLPPolicy/KLAfter 0.00400317 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.24943e-05 +GaussianMLPPolicy/LossBefore -5.5631e-10 +GaussianMLPPolicy/dLoss 4.24937e-05 +Iteration 307 +MetaTest/Average/AverageDiscountedReturn -47.8663 +MetaTest/Average/AverageReturn -47.8663 +MetaTest/Average/Iteration 307 +MetaTest/Average/MaxReturn -40.6978 +MetaTest/Average/MinReturn -57.6033 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.87443 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8663 +MetaTest/__unnamed_task__/AverageReturn -47.8663 +MetaTest/__unnamed_task__/Iteration 307 +MetaTest/__unnamed_task__/MaxReturn -40.6978 +MetaTest/__unnamed_task__/MinReturn -57.6033 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.87443 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4784e+07 +__unnamed_task__/AverageDiscountedReturn -27.909 +__unnamed_task__/AverageReturn -49.5095 +__unnamed_task__/Iteration 307 +__unnamed_task__/MaxReturn -39.5722 +__unnamed_task__/MinReturn -118.274 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.87854 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 18:19:36 | [maml_trainer] epoch #308 | Sampling for adapation and meta-testing... +2025-04-09 18:23:29 | [maml_trainer] epoch #308 | Finished meta-testing... +2025-04-09 18:23:29 | [maml_trainer] epoch #308 | Saving snapshot... +2025-04-09 18:23:51 | [maml_trainer] epoch #308 | Saved +2025-04-09 18:23:51 | [maml_trainer] epoch #308 | Time 524674.98 s +2025-04-09 18:23:51 | [maml_trainer] epoch #308 | EpochTime 1668.73 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8167 +Average/AverageReturn -49.8063 +Average/Iteration 308 +Average/MaxReturn -40.1189 +Average/MinReturn -76.2302 +Average/NumEpisodes 120 +Average/StdReturn 6.05789 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82389 +GaussianMLPPolicy/KLAfter 0.00389338 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.6718e-05 +GaussianMLPPolicy/LossBefore 1.72059e-08 +GaussianMLPPolicy/dLoss 1.67352e-05 +Iteration 308 +MetaTest/Average/AverageDiscountedReturn -46.5333 +MetaTest/Average/AverageReturn -46.5333 +MetaTest/Average/Iteration 308 +MetaTest/Average/MaxReturn -41.0288 +MetaTest/Average/MinReturn -51.9707 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.22733 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.5333 +MetaTest/__unnamed_task__/AverageReturn -46.5333 +MetaTest/__unnamed_task__/Iteration 308 +MetaTest/__unnamed_task__/MaxReturn -41.0288 +MetaTest/__unnamed_task__/MinReturn -51.9707 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.22733 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4832e+07 +__unnamed_task__/AverageDiscountedReturn -27.8167 +__unnamed_task__/AverageReturn -49.8063 +__unnamed_task__/Iteration 308 +__unnamed_task__/MaxReturn -40.1189 +__unnamed_task__/MinReturn -76.2302 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.05789 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 18:47:11 | [maml_trainer] epoch #309 | Sampling for adapation and meta-testing... +2025-04-09 18:51:00 | [maml_trainer] epoch #309 | Finished meta-testing... +2025-04-09 18:51:00 | [maml_trainer] epoch #309 | Saving snapshot... +2025-04-09 18:51:21 | [maml_trainer] epoch #309 | Saved +2025-04-09 18:51:21 | [maml_trainer] epoch #309 | Time 526325.00 s +2025-04-09 18:51:21 | [maml_trainer] epoch #309 | EpochTime 1650.01 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.773 +Average/AverageReturn -48.6486 +Average/Iteration 309 +Average/MaxReturn -39.6957 +Average/MinReturn -65.9791 +Average/NumEpisodes 120 +Average/StdReturn 4.87028 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.82256 +GaussianMLPPolicy/KLAfter 0.00348301 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000135588 +GaussianMLPPolicy/LossBefore -4.41074e-09 +GaussianMLPPolicy/dLoss -0.000135592 +Iteration 309 +MetaTest/Average/AverageDiscountedReturn -46.901 +MetaTest/Average/AverageReturn -46.901 +MetaTest/Average/Iteration 309 +MetaTest/Average/MaxReturn -41.5719 +MetaTest/Average/MinReturn -54.7417 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.52704 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.901 +MetaTest/__unnamed_task__/AverageReturn -46.901 +MetaTest/__unnamed_task__/Iteration 309 +MetaTest/__unnamed_task__/MaxReturn -41.5719 +MetaTest/__unnamed_task__/MinReturn -54.7417 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.52704 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.488e+07 +__unnamed_task__/AverageDiscountedReturn -27.773 +__unnamed_task__/AverageReturn -48.6486 +__unnamed_task__/Iteration 309 +__unnamed_task__/MaxReturn -39.6957 +__unnamed_task__/MinReturn -65.9791 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.87028 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 19:14:19 | [maml_trainer] epoch #310 | Sampling for adapation and meta-testing... +2025-04-09 19:18:09 | [maml_trainer] epoch #310 | Finished meta-testing... +2025-04-09 19:18:09 | [maml_trainer] epoch #310 | Saving snapshot... +2025-04-09 19:18:29 | [maml_trainer] epoch #310 | Saved +2025-04-09 19:18:29 | [maml_trainer] epoch #310 | Time 527953.67 s +2025-04-09 19:18:29 | [maml_trainer] epoch #310 | EpochTime 1628.67 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9675 +Average/AverageReturn -48.9213 +Average/Iteration 310 +Average/MaxReturn -28.3573 +Average/MinReturn -69.1885 +Average/NumEpisodes 120 +Average/StdReturn 5.68002 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.8197 +GaussianMLPPolicy/KLAfter 0.00133294 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.49466e-06 +GaussianMLPPolicy/LossBefore 1.02917e-08 +GaussianMLPPolicy/dLoss -3.48437e-06 +Iteration 310 +MetaTest/Average/AverageDiscountedReturn -48.1356 +MetaTest/Average/AverageReturn -48.1356 +MetaTest/Average/Iteration 310 +MetaTest/Average/MaxReturn -40.8584 +MetaTest/Average/MinReturn -62.1198 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.52934 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1356 +MetaTest/__unnamed_task__/AverageReturn -48.1356 +MetaTest/__unnamed_task__/Iteration 310 +MetaTest/__unnamed_task__/MaxReturn -40.8584 +MetaTest/__unnamed_task__/MinReturn -62.1198 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.52934 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4928e+07 +__unnamed_task__/AverageDiscountedReturn -27.9675 +__unnamed_task__/AverageReturn -48.9213 +__unnamed_task__/Iteration 310 +__unnamed_task__/MaxReturn -28.3573 +__unnamed_task__/MinReturn -69.1885 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.68002 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 19:41:23 | [maml_trainer] epoch #311 | Sampling for adapation and meta-testing... +2025-04-09 19:45:11 | [maml_trainer] epoch #311 | Finished meta-testing... +2025-04-09 19:45:11 | [maml_trainer] epoch #311 | Saving snapshot... +2025-04-09 19:45:32 | [maml_trainer] epoch #311 | Saved +2025-04-09 19:45:32 | [maml_trainer] epoch #311 | Time 529576.42 s +2025-04-09 19:45:32 | [maml_trainer] epoch #311 | EpochTime 1622.74 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8155 +Average/AverageReturn -48.7036 +Average/Iteration 311 +Average/MaxReturn -40.8717 +Average/MinReturn -82.5289 +Average/NumEpisodes 120 +Average/StdReturn 5.40684 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81716 +GaussianMLPPolicy/KLAfter 0.00135241 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.73656e-05 +GaussianMLPPolicy/LossBefore -9.97384e-09 +GaussianMLPPolicy/dLoss -3.73755e-05 +Iteration 311 +MetaTest/Average/AverageDiscountedReturn -48.4168 +MetaTest/Average/AverageReturn -48.4168 +MetaTest/Average/Iteration 311 +MetaTest/Average/MaxReturn -41.7705 +MetaTest/Average/MinReturn -60.7484 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.11815 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4168 +MetaTest/__unnamed_task__/AverageReturn -48.4168 +MetaTest/__unnamed_task__/Iteration 311 +MetaTest/__unnamed_task__/MaxReturn -41.7705 +MetaTest/__unnamed_task__/MinReturn -60.7484 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.11815 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.4976e+07 +__unnamed_task__/AverageDiscountedReturn -27.8155 +__unnamed_task__/AverageReturn -48.7036 +__unnamed_task__/Iteration 311 +__unnamed_task__/MaxReturn -40.8717 +__unnamed_task__/MinReturn -82.5289 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.40684 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 20:08:40 | [maml_trainer] epoch #312 | Sampling for adapation and meta-testing... +2025-04-09 20:12:33 | [maml_trainer] epoch #312 | Finished meta-testing... +2025-04-09 20:12:33 | [maml_trainer] epoch #312 | Saving snapshot... +2025-04-09 20:12:53 | [maml_trainer] epoch #312 | Saved +2025-04-09 20:12:53 | [maml_trainer] epoch #312 | Time 531217.76 s +2025-04-09 20:12:53 | [maml_trainer] epoch #312 | EpochTime 1641.34 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.166 +Average/AverageReturn -49.4382 +Average/Iteration 312 +Average/MaxReturn -39.0396 +Average/MinReturn -78.5957 +Average/NumEpisodes 120 +Average/StdReturn 5.12367 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81458 +GaussianMLPPolicy/KLAfter 0.00115265 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.1744e-05 +GaussianMLPPolicy/LossBefore -3.13918e-09 +GaussianMLPPolicy/dLoss 6.17409e-05 +Iteration 312 +MetaTest/Average/AverageDiscountedReturn -48.9259 +MetaTest/Average/AverageReturn -48.9259 +MetaTest/Average/Iteration 312 +MetaTest/Average/MaxReturn -39.6444 +MetaTest/Average/MinReturn -61.2597 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.18456 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9259 +MetaTest/__unnamed_task__/AverageReturn -48.9259 +MetaTest/__unnamed_task__/Iteration 312 +MetaTest/__unnamed_task__/MaxReturn -39.6444 +MetaTest/__unnamed_task__/MinReturn -61.2597 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.18456 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5024e+07 +__unnamed_task__/AverageDiscountedReturn -28.166 +__unnamed_task__/AverageReturn -49.4382 +__unnamed_task__/Iteration 312 +__unnamed_task__/MaxReturn -39.0396 +__unnamed_task__/MinReturn -78.5957 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.12367 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 20:35:52 | [maml_trainer] epoch #313 | Sampling for adapation and meta-testing... +2025-04-09 20:39:41 | [maml_trainer] epoch #313 | Finished meta-testing... +2025-04-09 20:39:41 | [maml_trainer] epoch #313 | Saving snapshot... +2025-04-09 20:40:01 | [maml_trainer] epoch #313 | Saved +2025-04-09 20:40:01 | [maml_trainer] epoch #313 | Time 532845.78 s +2025-04-09 20:40:01 | [maml_trainer] epoch #313 | EpochTime 1628.01 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6974 +Average/AverageReturn -48.5032 +Average/Iteration 313 +Average/MaxReturn -39.1361 +Average/MinReturn -64.4651 +Average/NumEpisodes 120 +Average/StdReturn 4.73379 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.81215 +GaussianMLPPolicy/KLAfter 0.0011516 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.43742e-05 +GaussianMLPPolicy/LossBefore -5.32468e-09 +GaussianMLPPolicy/dLoss 1.43689e-05 +Iteration 313 +MetaTest/Average/AverageDiscountedReturn -50.1114 +MetaTest/Average/AverageReturn -50.1114 +MetaTest/Average/Iteration 313 +MetaTest/Average/MaxReturn -42.1314 +MetaTest/Average/MinReturn -61.7244 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.71427 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1114 +MetaTest/__unnamed_task__/AverageReturn -50.1114 +MetaTest/__unnamed_task__/Iteration 313 +MetaTest/__unnamed_task__/MaxReturn -42.1314 +MetaTest/__unnamed_task__/MinReturn -61.7244 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.71427 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5072e+07 +__unnamed_task__/AverageDiscountedReturn -27.6974 +__unnamed_task__/AverageReturn -48.5032 +__unnamed_task__/Iteration 313 +__unnamed_task__/MaxReturn -39.1361 +__unnamed_task__/MinReturn -64.4651 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.73379 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 21:02:52 | [maml_trainer] epoch #314 | Sampling for adapation and meta-testing... +2025-04-09 21:06:48 | [maml_trainer] epoch #314 | Finished meta-testing... +2025-04-09 21:06:48 | [maml_trainer] epoch #314 | Saving snapshot... +2025-04-09 21:07:10 | [maml_trainer] epoch #314 | Saved +2025-04-09 21:07:10 | [maml_trainer] epoch #314 | Time 534473.98 s +2025-04-09 21:07:10 | [maml_trainer] epoch #314 | EpochTime 1628.20 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.5821 +Average/AverageReturn -48.5143 +Average/Iteration 314 +Average/MaxReturn -40.5111 +Average/MinReturn -60.6104 +Average/NumEpisodes 120 +Average/StdReturn 4.30856 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.80983 +GaussianMLPPolicy/KLAfter 0.00122925 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000116118 +GaussianMLPPolicy/LossBefore 1.10467e-08 +GaussianMLPPolicy/dLoss 0.000116129 +Iteration 314 +MetaTest/Average/AverageDiscountedReturn -48.7797 +MetaTest/Average/AverageReturn -48.7797 +MetaTest/Average/Iteration 314 +MetaTest/Average/MaxReturn -39.9255 +MetaTest/Average/MinReturn -58.1924 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.66646 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7797 +MetaTest/__unnamed_task__/AverageReturn -48.7797 +MetaTest/__unnamed_task__/Iteration 314 +MetaTest/__unnamed_task__/MaxReturn -39.9255 +MetaTest/__unnamed_task__/MinReturn -58.1924 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.66646 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.512e+07 +__unnamed_task__/AverageDiscountedReturn -27.5821 +__unnamed_task__/AverageReturn -48.5143 +__unnamed_task__/Iteration 314 +__unnamed_task__/MaxReturn -40.5111 +__unnamed_task__/MinReturn -60.6104 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.30856 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 21:30:25 | [maml_trainer] epoch #315 | Sampling for adapation and meta-testing... +2025-04-09 21:34:18 | [maml_trainer] epoch #315 | Finished meta-testing... +2025-04-09 21:34:18 | [maml_trainer] epoch #315 | Saving snapshot... +2025-04-09 21:34:40 | [maml_trainer] epoch #315 | Saved +2025-04-09 21:34:40 | [maml_trainer] epoch #315 | Time 536124.83 s +2025-04-09 21:34:40 | [maml_trainer] epoch #315 | EpochTime 1650.85 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.4121 +Average/AverageReturn -50.5 +Average/Iteration 315 +Average/MaxReturn -40.5755 +Average/MinReturn -101.82 +Average/NumEpisodes 120 +Average/StdReturn 8.57065 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.80692 +GaussianMLPPolicy/KLAfter 0.000818868 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.00618e-05 +GaussianMLPPolicy/LossBefore 7.82808e-09 +GaussianMLPPolicy/dLoss 4.00696e-05 +Iteration 315 +MetaTest/Average/AverageDiscountedReturn -46.9649 +MetaTest/Average/AverageReturn -46.9649 +MetaTest/Average/Iteration 315 +MetaTest/Average/MaxReturn -40.1447 +MetaTest/Average/MinReturn -59.7469 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.6597 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9649 +MetaTest/__unnamed_task__/AverageReturn -46.9649 +MetaTest/__unnamed_task__/Iteration 315 +MetaTest/__unnamed_task__/MaxReturn -40.1447 +MetaTest/__unnamed_task__/MinReturn -59.7469 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.6597 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5168e+07 +__unnamed_task__/AverageDiscountedReturn -28.4121 +__unnamed_task__/AverageReturn -50.5 +__unnamed_task__/Iteration 315 +__unnamed_task__/MaxReturn -40.5755 +__unnamed_task__/MinReturn -101.82 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.57065 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 21:57:57 | [maml_trainer] epoch #316 | Sampling for adapation and meta-testing... +2025-04-09 22:01:49 | [maml_trainer] epoch #316 | Finished meta-testing... +2025-04-09 22:01:49 | [maml_trainer] epoch #316 | Saving snapshot... +2025-04-09 22:02:10 | [maml_trainer] epoch #316 | Saved +2025-04-09 22:02:10 | [maml_trainer] epoch #316 | Time 537774.87 s +2025-04-09 22:02:10 | [maml_trainer] epoch #316 | EpochTime 1650.04 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9429 +Average/AverageReturn -49.0744 +Average/Iteration 316 +Average/MaxReturn -19.9619 +Average/MinReturn -66.6264 +Average/NumEpisodes 120 +Average/StdReturn 5.33786 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.80458 +GaussianMLPPolicy/KLAfter 0.000614073 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.06728e-06 +GaussianMLPPolicy/LossBefore -6.95387e-09 +GaussianMLPPolicy/dLoss 7.06033e-06 +Iteration 316 +MetaTest/Average/AverageDiscountedReturn -48.1477 +MetaTest/Average/AverageReturn -48.1477 +MetaTest/Average/Iteration 316 +MetaTest/Average/MaxReturn -43.5424 +MetaTest/Average/MinReturn -55.9286 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.74069 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1477 +MetaTest/__unnamed_task__/AverageReturn -48.1477 +MetaTest/__unnamed_task__/Iteration 316 +MetaTest/__unnamed_task__/MaxReturn -43.5424 +MetaTest/__unnamed_task__/MinReturn -55.9286 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.74069 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5216e+07 +__unnamed_task__/AverageDiscountedReturn -27.9429 +__unnamed_task__/AverageReturn -49.0744 +__unnamed_task__/Iteration 316 +__unnamed_task__/MaxReturn -19.9619 +__unnamed_task__/MinReturn -66.6264 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.33786 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 22:25:27 | [maml_trainer] epoch #317 | Sampling for adapation and meta-testing... +2025-04-09 22:29:18 | [maml_trainer] epoch #317 | Finished meta-testing... +2025-04-09 22:29:18 | [maml_trainer] epoch #317 | Saving snapshot... +2025-04-09 22:29:40 | [maml_trainer] epoch #317 | Saved +2025-04-09 22:29:40 | [maml_trainer] epoch #317 | Time 539424.42 s +2025-04-09 22:29:40 | [maml_trainer] epoch #317 | EpochTime 1649.54 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.2763 +Average/AverageReturn -50.4668 +Average/Iteration 317 +Average/MaxReturn -40.4743 +Average/MinReturn -104.348 +Average/NumEpisodes 120 +Average/StdReturn 8.11673 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.80352 +GaussianMLPPolicy/KLAfter 0.00192482 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.05457e-06 +GaussianMLPPolicy/LossBefore 5.96046e-10 +GaussianMLPPolicy/dLoss -2.05398e-06 +Iteration 317 +MetaTest/Average/AverageDiscountedReturn -49.9519 +MetaTest/Average/AverageReturn -49.9519 +MetaTest/Average/Iteration 317 +MetaTest/Average/MaxReturn -41.888 +MetaTest/Average/MinReturn -66.2888 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.0156 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9519 +MetaTest/__unnamed_task__/AverageReturn -49.9519 +MetaTest/__unnamed_task__/Iteration 317 +MetaTest/__unnamed_task__/MaxReturn -41.888 +MetaTest/__unnamed_task__/MinReturn -66.2888 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.0156 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5264e+07 +__unnamed_task__/AverageDiscountedReturn -28.2763 +__unnamed_task__/AverageReturn -50.4668 +__unnamed_task__/Iteration 317 +__unnamed_task__/MaxReturn -40.4743 +__unnamed_task__/MinReturn -104.348 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.11673 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-09 22:52:35 | [maml_trainer] epoch #318 | Sampling for adapation and meta-testing... +2025-04-09 22:56:26 | [maml_trainer] epoch #318 | Finished meta-testing... +2025-04-09 22:56:26 | [maml_trainer] epoch #318 | Saving snapshot... +2025-04-09 22:56:48 | [maml_trainer] epoch #318 | Saved +2025-04-09 22:56:48 | [maml_trainer] epoch #318 | Time 541051.98 s +2025-04-09 22:56:48 | [maml_trainer] epoch #318 | EpochTime 1627.56 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3098 +Average/AverageReturn -49.6881 +Average/Iteration 318 +Average/MaxReturn -41.5239 +Average/MinReturn -66.5557 +Average/NumEpisodes 120 +Average/StdReturn 5.66451 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.80054 +GaussianMLPPolicy/KLAfter 0.00142553 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.48565e-05 +GaussianMLPPolicy/LossBefore 1.03315e-09 +GaussianMLPPolicy/dLoss -4.48554e-05 +Iteration 318 +MetaTest/Average/AverageDiscountedReturn -47.3771 +MetaTest/Average/AverageReturn -47.3771 +MetaTest/Average/Iteration 318 +MetaTest/Average/MaxReturn -23.7403 +MetaTest/Average/MinReturn -59.3939 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.38295 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.3771 +MetaTest/__unnamed_task__/AverageReturn -47.3771 +MetaTest/__unnamed_task__/Iteration 318 +MetaTest/__unnamed_task__/MaxReturn -23.7403 +MetaTest/__unnamed_task__/MinReturn -59.3939 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.38295 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5312e+07 +__unnamed_task__/AverageDiscountedReturn -28.3098 +__unnamed_task__/AverageReturn -49.6881 +__unnamed_task__/Iteration 318 +__unnamed_task__/MaxReturn -41.5239 +__unnamed_task__/MinReturn -66.5557 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.66451 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 23:19:51 | [maml_trainer] epoch #319 | Sampling for adapation and meta-testing... +2025-04-09 23:23:42 | [maml_trainer] epoch #319 | Finished meta-testing... +2025-04-09 23:23:42 | [maml_trainer] epoch #319 | Saving snapshot... +2025-04-09 23:24:03 | [maml_trainer] epoch #319 | Saved +2025-04-09 23:24:03 | [maml_trainer] epoch #319 | Time 542687.67 s +2025-04-09 23:24:03 | [maml_trainer] epoch #319 | EpochTime 1635.69 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1834 +Average/AverageReturn -49.2963 +Average/Iteration 319 +Average/MaxReturn -40.0543 +Average/MinReturn -64.6422 +Average/NumEpisodes 120 +Average/StdReturn 4.69928 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79704 +GaussianMLPPolicy/KLAfter 0.00118412 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.40821e-05 +GaussianMLPPolicy/LossBefore 8.22544e-09 +GaussianMLPPolicy/dLoss 1.40903e-05 +Iteration 319 +MetaTest/Average/AverageDiscountedReturn -48.4965 +MetaTest/Average/AverageReturn -48.4965 +MetaTest/Average/Iteration 319 +MetaTest/Average/MaxReturn -43.0421 +MetaTest/Average/MinReturn -60.7143 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.82871 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4965 +MetaTest/__unnamed_task__/AverageReturn -48.4965 +MetaTest/__unnamed_task__/Iteration 319 +MetaTest/__unnamed_task__/MaxReturn -43.0421 +MetaTest/__unnamed_task__/MinReturn -60.7143 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.82871 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.536e+07 +__unnamed_task__/AverageDiscountedReturn -28.1834 +__unnamed_task__/AverageReturn -49.2963 +__unnamed_task__/Iteration 319 +__unnamed_task__/MaxReturn -40.0543 +__unnamed_task__/MinReturn -64.6422 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.69928 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-09 23:47:20 | [maml_trainer] epoch #320 | Sampling for adapation and meta-testing... +2025-04-09 23:51:08 | [maml_trainer] epoch #320 | Finished meta-testing... +2025-04-09 23:51:08 | [maml_trainer] epoch #320 | Saving snapshot... +2025-04-09 23:51:28 | [maml_trainer] epoch #320 | Saved +2025-04-09 23:51:28 | [maml_trainer] epoch #320 | Time 544332.83 s +2025-04-09 23:51:28 | [maml_trainer] epoch #320 | EpochTime 1645.15 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.5541 +Average/AverageReturn -50.4466 +Average/Iteration 320 +Average/MaxReturn -41.9554 +Average/MinReturn -108.378 +Average/NumEpisodes 120 +Average/StdReturn 7.24352 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79413 +GaussianMLPPolicy/KLAfter 0.00141039 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.25041e-05 +GaussianMLPPolicy/LossBefore 1.98682e-09 +GaussianMLPPolicy/dLoss 3.25061e-05 +Iteration 320 +MetaTest/Average/AverageDiscountedReturn -50.5686 +MetaTest/Average/AverageReturn -50.5686 +MetaTest/Average/Iteration 320 +MetaTest/Average/MaxReturn -43.7113 +MetaTest/Average/MinReturn -64.0862 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.1625 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5686 +MetaTest/__unnamed_task__/AverageReturn -50.5686 +MetaTest/__unnamed_task__/Iteration 320 +MetaTest/__unnamed_task__/MaxReturn -43.7113 +MetaTest/__unnamed_task__/MinReturn -64.0862 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.1625 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5408e+07 +__unnamed_task__/AverageDiscountedReturn -28.5541 +__unnamed_task__/AverageReturn -50.4466 +__unnamed_task__/Iteration 320 +__unnamed_task__/MaxReturn -41.9554 +__unnamed_task__/MinReturn -108.378 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.24352 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 00:14:39 | [maml_trainer] epoch #321 | Sampling for adapation and meta-testing... +2025-04-10 00:18:31 | [maml_trainer] epoch #321 | Finished meta-testing... +2025-04-10 00:18:31 | [maml_trainer] epoch #321 | Saving snapshot... +2025-04-10 00:18:52 | [maml_trainer] epoch #321 | Saved +2025-04-10 00:18:52 | [maml_trainer] epoch #321 | Time 545976.25 s +2025-04-10 00:18:52 | [maml_trainer] epoch #321 | EpochTime 1643.41 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9938 +Average/AverageReturn -48.6746 +Average/Iteration 321 +Average/MaxReturn -39.8114 +Average/MinReturn -73.2399 +Average/NumEpisodes 120 +Average/StdReturn 5.21137 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79191 +GaussianMLPPolicy/KLAfter 0.00137778 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.85831e-05 +GaussianMLPPolicy/LossBefore 1.12057e-08 +GaussianMLPPolicy/dLoss -4.85719e-05 +Iteration 321 +MetaTest/Average/AverageDiscountedReturn -49.3972 +MetaTest/Average/AverageReturn -49.3972 +MetaTest/Average/Iteration 321 +MetaTest/Average/MaxReturn -40.4729 +MetaTest/Average/MinReturn -60.0459 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.78592 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3972 +MetaTest/__unnamed_task__/AverageReturn -49.3972 +MetaTest/__unnamed_task__/Iteration 321 +MetaTest/__unnamed_task__/MaxReturn -40.4729 +MetaTest/__unnamed_task__/MinReturn -60.0459 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.78592 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5456e+07 +__unnamed_task__/AverageDiscountedReturn -27.9938 +__unnamed_task__/AverageReturn -48.6746 +__unnamed_task__/Iteration 321 +__unnamed_task__/MaxReturn -39.8114 +__unnamed_task__/MinReturn -73.2399 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.21137 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 00:41:49 | [maml_trainer] epoch #322 | Sampling for adapation and meta-testing... +2025-04-10 00:45:36 | [maml_trainer] epoch #322 | Finished meta-testing... +2025-04-10 00:45:36 | [maml_trainer] epoch #322 | Saving snapshot... +2025-04-10 00:45:58 | [maml_trainer] epoch #322 | Saved +2025-04-10 00:45:58 | [maml_trainer] epoch #322 | Time 547602.56 s +2025-04-10 00:45:58 | [maml_trainer] epoch #322 | EpochTime 1626.31 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.9568 +Average/AverageReturn -51.1436 +Average/Iteration 322 +Average/MaxReturn -40.9545 +Average/MinReturn -79.3995 +Average/NumEpisodes 120 +Average/StdReturn 6.73153 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79014 +GaussianMLPPolicy/KLAfter 0.000991551 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.45834e-05 +GaussianMLPPolicy/LossBefore -4.88758e-09 +GaussianMLPPolicy/dLoss -8.45883e-05 +Iteration 322 +MetaTest/Average/AverageDiscountedReturn -57.1051 +MetaTest/Average/AverageReturn -57.1051 +MetaTest/Average/Iteration 322 +MetaTest/Average/MaxReturn -40.8436 +MetaTest/Average/MinReturn -157.831 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 23.917 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -57.1051 +MetaTest/__unnamed_task__/AverageReturn -57.1051 +MetaTest/__unnamed_task__/Iteration 322 +MetaTest/__unnamed_task__/MaxReturn -40.8436 +MetaTest/__unnamed_task__/MinReturn -157.831 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 23.917 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5504e+07 +__unnamed_task__/AverageDiscountedReturn -28.9568 +__unnamed_task__/AverageReturn -51.1436 +__unnamed_task__/Iteration 322 +__unnamed_task__/MaxReturn -40.9545 +__unnamed_task__/MinReturn -79.3995 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.73153 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 01:08:48 | [maml_trainer] epoch #323 | Sampling for adapation and meta-testing... +2025-04-10 01:12:39 | [maml_trainer] epoch #323 | Finished meta-testing... +2025-04-10 01:12:39 | [maml_trainer] epoch #323 | Saving snapshot... +2025-04-10 01:13:01 | [maml_trainer] epoch #323 | Saved +2025-04-10 01:13:01 | [maml_trainer] epoch #323 | Time 549225.18 s +2025-04-10 01:13:01 | [maml_trainer] epoch #323 | EpochTime 1622.61 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.5042 +Average/AverageReturn -50.1699 +Average/Iteration 323 +Average/MaxReturn -39.1193 +Average/MinReturn -86.5068 +Average/NumEpisodes 120 +Average/StdReturn 5.98316 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78795 +GaussianMLPPolicy/KLAfter 0.000823584 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.21056e-05 +GaussianMLPPolicy/LossBefore 1.3868e-08 +GaussianMLPPolicy/dLoss 3.21194e-05 +Iteration 323 +MetaTest/Average/AverageDiscountedReturn -55.1664 +MetaTest/Average/AverageReturn -55.1664 +MetaTest/Average/Iteration 323 +MetaTest/Average/MaxReturn -41.0702 +MetaTest/Average/MinReturn -164.471 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.5671 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.1664 +MetaTest/__unnamed_task__/AverageReturn -55.1664 +MetaTest/__unnamed_task__/Iteration 323 +MetaTest/__unnamed_task__/MaxReturn -41.0702 +MetaTest/__unnamed_task__/MinReturn -164.471 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.5671 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5552e+07 +__unnamed_task__/AverageDiscountedReturn -28.5042 +__unnamed_task__/AverageReturn -50.1699 +__unnamed_task__/Iteration 323 +__unnamed_task__/MaxReturn -39.1193 +__unnamed_task__/MinReturn -86.5068 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.98316 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 01:36:09 | [maml_trainer] epoch #324 | Sampling for adapation and meta-testing... +2025-04-10 01:39:57 | [maml_trainer] epoch #324 | Finished meta-testing... +2025-04-10 01:39:57 | [maml_trainer] epoch #324 | Saving snapshot... +2025-04-10 01:40:19 | [maml_trainer] epoch #324 | Saved +2025-04-10 01:40:19 | [maml_trainer] epoch #324 | Time 550863.14 s +2025-04-10 01:40:19 | [maml_trainer] epoch #324 | EpochTime 1637.96 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.8588 +Average/AverageReturn -50.7787 +Average/Iteration 324 +Average/MaxReturn -40.904 +Average/MinReturn -82.363 +Average/NumEpisodes 120 +Average/StdReturn 6.25395 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78732 +GaussianMLPPolicy/KLAfter 0.00114626 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.00042e-05 +GaussianMLPPolicy/LossBefore -3.69549e-09 +GaussianMLPPolicy/dLoss 9.00005e-05 +Iteration 324 +MetaTest/Average/AverageDiscountedReturn -49.8347 +MetaTest/Average/AverageReturn -49.8347 +MetaTest/Average/Iteration 324 +MetaTest/Average/MaxReturn -43.1957 +MetaTest/Average/MinReturn -69.8567 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.59161 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8347 +MetaTest/__unnamed_task__/AverageReturn -49.8347 +MetaTest/__unnamed_task__/Iteration 324 +MetaTest/__unnamed_task__/MaxReturn -43.1957 +MetaTest/__unnamed_task__/MinReturn -69.8567 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.59161 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.56e+07 +__unnamed_task__/AverageDiscountedReturn -28.8588 +__unnamed_task__/AverageReturn -50.7787 +__unnamed_task__/Iteration 324 +__unnamed_task__/MaxReturn -40.904 +__unnamed_task__/MinReturn -82.363 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.25395 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 02:03:21 | [maml_trainer] epoch #325 | Sampling for adapation and meta-testing... +2025-04-10 02:07:15 | [maml_trainer] epoch #325 | Finished meta-testing... +2025-04-10 02:07:15 | [maml_trainer] epoch #325 | Saving snapshot... +2025-04-10 02:07:37 | [maml_trainer] epoch #325 | Saved +2025-04-10 02:07:37 | [maml_trainer] epoch #325 | Time 552501.64 s +2025-04-10 02:07:37 | [maml_trainer] epoch #325 | EpochTime 1638.50 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.0843 +Average/AverageReturn -48.7862 +Average/Iteration 325 +Average/MaxReturn -40.0531 +Average/MinReturn -65.0957 +Average/NumEpisodes 120 +Average/StdReturn 4.69157 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78759 +GaussianMLPPolicy/KLAfter 0.00270296 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.74927e-05 +GaussianMLPPolicy/LossBefore -1.11659e-08 +GaussianMLPPolicy/dLoss -6.75039e-05 +Iteration 325 +MetaTest/Average/AverageDiscountedReturn -50.8461 +MetaTest/Average/AverageReturn -50.8461 +MetaTest/Average/Iteration 325 +MetaTest/Average/MaxReturn -42.4328 +MetaTest/Average/MinReturn -59.6953 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.38259 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8461 +MetaTest/__unnamed_task__/AverageReturn -50.8461 +MetaTest/__unnamed_task__/Iteration 325 +MetaTest/__unnamed_task__/MaxReturn -42.4328 +MetaTest/__unnamed_task__/MinReturn -59.6953 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.38259 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5648e+07 +__unnamed_task__/AverageDiscountedReturn -28.0843 +__unnamed_task__/AverageReturn -48.7862 +__unnamed_task__/Iteration 325 +__unnamed_task__/MaxReturn -40.0531 +__unnamed_task__/MinReturn -65.0957 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.69157 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 02:31:05 | [maml_trainer] epoch #326 | Sampling for adapation and meta-testing... +2025-04-10 02:34:57 | [maml_trainer] epoch #326 | Finished meta-testing... +2025-04-10 02:34:57 | [maml_trainer] epoch #326 | Saving snapshot... +2025-04-10 02:35:19 | [maml_trainer] epoch #326 | Saved +2025-04-10 02:35:19 | [maml_trainer] epoch #326 | Time 554163.84 s +2025-04-10 02:35:19 | [maml_trainer] epoch #326 | EpochTime 1662.19 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -28.4548 +Average/AverageReturn -50.6804 +Average/Iteration 326 +Average/MaxReturn -40.2213 +Average/MinReturn -123.592 +Average/NumEpisodes 120 +Average/StdReturn 8.68516 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78873 +GaussianMLPPolicy/KLAfter 0.00223398 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.49662e-05 +GaussianMLPPolicy/LossBefore -5.80152e-09 +GaussianMLPPolicy/dLoss 4.49604e-05 +Iteration 326 +MetaTest/Average/AverageDiscountedReturn -50.0578 +MetaTest/Average/AverageReturn -50.0578 +MetaTest/Average/Iteration 326 +MetaTest/Average/MaxReturn -42.5623 +MetaTest/Average/MinReturn -58.6447 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.62377 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0578 +MetaTest/__unnamed_task__/AverageReturn -50.0578 +MetaTest/__unnamed_task__/Iteration 326 +MetaTest/__unnamed_task__/MaxReturn -42.5623 +MetaTest/__unnamed_task__/MinReturn -58.6447 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.62377 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5696e+07 +__unnamed_task__/AverageDiscountedReturn -28.4548 +__unnamed_task__/AverageReturn -50.6804 +__unnamed_task__/Iteration 326 +__unnamed_task__/MaxReturn -40.2213 +__unnamed_task__/MinReturn -123.592 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.68516 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 02:58:28 | [maml_trainer] epoch #327 | Sampling for adapation and meta-testing... +2025-04-10 03:02:19 | [maml_trainer] epoch #327 | Finished meta-testing... +2025-04-10 03:02:19 | [maml_trainer] epoch #327 | Saving snapshot... +2025-04-10 03:02:41 | [maml_trainer] epoch #327 | Saved +2025-04-10 03:02:41 | [maml_trainer] epoch #327 | Time 555805.14 s +2025-04-10 03:02:41 | [maml_trainer] epoch #327 | EpochTime 1641.30 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.4046 +Average/AverageReturn -49.8677 +Average/Iteration 327 +Average/MaxReturn -41.7436 +Average/MinReturn -74.4111 +Average/NumEpisodes 120 +Average/StdReturn 5.93408 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78988 +GaussianMLPPolicy/KLAfter 0.00193486 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.1155e-05 +GaussianMLPPolicy/LossBefore 8.30491e-09 +GaussianMLPPolicy/dLoss -2.11467e-05 +Iteration 327 +MetaTest/Average/AverageDiscountedReturn -49.817 +MetaTest/Average/AverageReturn -49.817 +MetaTest/Average/Iteration 327 +MetaTest/Average/MaxReturn -43.9217 +MetaTest/Average/MinReturn -57.3454 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.5962 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.817 +MetaTest/__unnamed_task__/AverageReturn -49.817 +MetaTest/__unnamed_task__/Iteration 327 +MetaTest/__unnamed_task__/MaxReturn -43.9217 +MetaTest/__unnamed_task__/MinReturn -57.3454 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.5962 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5744e+07 +__unnamed_task__/AverageDiscountedReturn -28.4046 +__unnamed_task__/AverageReturn -49.8677 +__unnamed_task__/Iteration 327 +__unnamed_task__/MaxReturn -41.7436 +__unnamed_task__/MinReturn -74.4111 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.93408 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 03:53:09 | [maml_trainer] epoch #328 | Sampling for adapation and meta-testing... +2025-04-10 04:02:50 | [maml_trainer] epoch #328 | Finished meta-testing... +2025-04-10 04:02:50 | [maml_trainer] epoch #328 | Saving snapshot... +2025-04-10 04:03:39 | [maml_trainer] epoch #328 | Saved +2025-04-10 04:03:39 | [maml_trainer] epoch #328 | Time 559463.66 s +2025-04-10 04:03:39 | [maml_trainer] epoch #328 | EpochTime 3658.51 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1596 +Average/AverageReturn -49.1912 +Average/Iteration 328 +Average/MaxReturn -40.5991 +Average/MinReturn -65.9819 +Average/NumEpisodes 120 +Average/StdReturn 5.19057 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79062 +GaussianMLPPolicy/KLAfter 0.00165614 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.52652e-05 +GaussianMLPPolicy/LossBefore -5.28494e-09 +GaussianMLPPolicy/dLoss 4.52599e-05 +Iteration 328 +MetaTest/Average/AverageDiscountedReturn -47.8255 +MetaTest/Average/AverageReturn -47.8255 +MetaTest/Average/Iteration 328 +MetaTest/Average/MaxReturn -41.9097 +MetaTest/Average/MinReturn -57.8147 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.55548 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.8255 +MetaTest/__unnamed_task__/AverageReturn -47.8255 +MetaTest/__unnamed_task__/Iteration 328 +MetaTest/__unnamed_task__/MaxReturn -41.9097 +MetaTest/__unnamed_task__/MinReturn -57.8147 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.55548 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5792e+07 +__unnamed_task__/AverageDiscountedReturn -28.1596 +__unnamed_task__/AverageReturn -49.1912 +__unnamed_task__/Iteration 328 +__unnamed_task__/MaxReturn -40.5991 +__unnamed_task__/MinReturn -65.9819 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.19057 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 05:00:46 | [maml_trainer] epoch #329 | Sampling for adapation and meta-testing... +2025-04-10 05:09:49 | [maml_trainer] epoch #329 | Finished meta-testing... +2025-04-10 05:09:49 | [maml_trainer] epoch #329 | Saving snapshot... +2025-04-10 05:10:55 | [maml_trainer] epoch #329 | Saved +2025-04-10 05:10:55 | [maml_trainer] epoch #329 | Time 563499.22 s +2025-04-10 05:10:55 | [maml_trainer] epoch #329 | EpochTime 4035.56 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.5295 +Average/AverageReturn -50.0785 +Average/Iteration 329 +Average/MaxReturn -41.1459 +Average/MinReturn -68.1184 +Average/NumEpisodes 120 +Average/StdReturn 5.17596 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79125 +GaussianMLPPolicy/KLAfter 0.00374429 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.10536e-05 +GaussianMLPPolicy/LossBefore 3.17891e-09 +GaussianMLPPolicy/dLoss 7.10568e-05 +Iteration 329 +MetaTest/Average/AverageDiscountedReturn -47.2637 +MetaTest/Average/AverageReturn -47.2637 +MetaTest/Average/Iteration 329 +MetaTest/Average/MaxReturn -43.1479 +MetaTest/Average/MinReturn -54.2962 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.80012 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2637 +MetaTest/__unnamed_task__/AverageReturn -47.2637 +MetaTest/__unnamed_task__/Iteration 329 +MetaTest/__unnamed_task__/MaxReturn -43.1479 +MetaTest/__unnamed_task__/MinReturn -54.2962 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.80012 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.584e+07 +__unnamed_task__/AverageDiscountedReturn -28.5295 +__unnamed_task__/AverageReturn -50.0785 +__unnamed_task__/Iteration 329 +__unnamed_task__/MaxReturn -41.1459 +__unnamed_task__/MinReturn -68.1184 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.17596 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 05:48:04 | [maml_trainer] epoch #330 | Sampling for adapation and meta-testing... +2025-04-10 05:52:46 | [maml_trainer] epoch #330 | Finished meta-testing... +2025-04-10 05:52:46 | [maml_trainer] epoch #330 | Saving snapshot... +2025-04-10 05:53:08 | [maml_trainer] epoch #330 | Saved +2025-04-10 05:53:08 | [maml_trainer] epoch #330 | Time 566031.99 s +2025-04-10 05:53:08 | [maml_trainer] epoch #330 | EpochTime 2532.76 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.1954 +Average/AverageReturn -49.2518 +Average/Iteration 330 +Average/MaxReturn -39.8271 +Average/MinReturn -65.9496 +Average/NumEpisodes 120 +Average/StdReturn 4.4446 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79126 +GaussianMLPPolicy/KLAfter 0.00447978 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.9987e-05 +GaussianMLPPolicy/LossBefore -3.61602e-09 +GaussianMLPPolicy/dLoss -8.99907e-05 +Iteration 330 +MetaTest/Average/AverageDiscountedReturn -50.478 +MetaTest/Average/AverageReturn -50.478 +MetaTest/Average/Iteration 330 +MetaTest/Average/MaxReturn -43.7745 +MetaTest/Average/MinReturn -63.1525 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.2218 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.478 +MetaTest/__unnamed_task__/AverageReturn -50.478 +MetaTest/__unnamed_task__/Iteration 330 +MetaTest/__unnamed_task__/MaxReturn -43.7745 +MetaTest/__unnamed_task__/MinReturn -63.1525 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.2218 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5888e+07 +__unnamed_task__/AverageDiscountedReturn -28.1954 +__unnamed_task__/AverageReturn -49.2518 +__unnamed_task__/Iteration 330 +__unnamed_task__/MaxReturn -39.8271 +__unnamed_task__/MinReturn -65.9496 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.4446 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 06:16:18 | [maml_trainer] epoch #331 | Sampling for adapation and meta-testing... +2025-04-10 06:20:09 | [maml_trainer] epoch #331 | Finished meta-testing... +2025-04-10 06:20:09 | [maml_trainer] epoch #331 | Saving snapshot... +2025-04-10 06:20:30 | [maml_trainer] epoch #331 | Saved +2025-04-10 06:20:30 | [maml_trainer] epoch #331 | Time 567674.51 s +2025-04-10 06:20:30 | [maml_trainer] epoch #331 | EpochTime 1642.52 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.931 +Average/AverageReturn -49.2678 +Average/Iteration 331 +Average/MaxReturn -42.3299 +Average/MinReturn -64.5102 +Average/NumEpisodes 120 +Average/StdReturn 4.34228 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79134 +GaussianMLPPolicy/KLAfter 0.00569084 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.9758e-05 +GaussianMLPPolicy/LossBefore -2.86102e-09 +GaussianMLPPolicy/dLoss 4.97551e-05 +Iteration 331 +MetaTest/Average/AverageDiscountedReturn -48.1913 +MetaTest/Average/AverageReturn -48.1913 +MetaTest/Average/Iteration 331 +MetaTest/Average/MaxReturn -42.6202 +MetaTest/Average/MinReturn -55.8029 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.41871 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1913 +MetaTest/__unnamed_task__/AverageReturn -48.1913 +MetaTest/__unnamed_task__/Iteration 331 +MetaTest/__unnamed_task__/MaxReturn -42.6202 +MetaTest/__unnamed_task__/MinReturn -55.8029 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.41871 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5936e+07 +__unnamed_task__/AverageDiscountedReturn -27.931 +__unnamed_task__/AverageReturn -49.2678 +__unnamed_task__/Iteration 331 +__unnamed_task__/MaxReturn -42.3299 +__unnamed_task__/MinReturn -64.5102 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.34228 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 06:43:53 | [maml_trainer] epoch #332 | Sampling for adapation and meta-testing... +2025-04-10 06:47:47 | [maml_trainer] epoch #332 | Finished meta-testing... +2025-04-10 06:47:47 | [maml_trainer] epoch #332 | Saving snapshot... +2025-04-10 06:48:08 | [maml_trainer] epoch #332 | Saved +2025-04-10 06:48:08 | [maml_trainer] epoch #332 | Time 569332.17 s +2025-04-10 06:48:08 | [maml_trainer] epoch #332 | EpochTime 1657.65 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -28.3426 +Average/AverageReturn -50.6164 +Average/Iteration 332 +Average/MaxReturn -43.4737 +Average/MinReturn -69.6072 +Average/NumEpisodes 120 +Average/StdReturn 4.74619 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7906 +GaussianMLPPolicy/KLAfter 0.00453074 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.98009e-05 +GaussianMLPPolicy/LossBefore 4.09285e-09 +GaussianMLPPolicy/dLoss 6.9805e-05 +Iteration 332 +MetaTest/Average/AverageDiscountedReturn -51.1091 +MetaTest/Average/AverageReturn -51.1091 +MetaTest/Average/Iteration 332 +MetaTest/Average/MaxReturn -44.34 +MetaTest/Average/MinReturn -65.4998 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.47079 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.1091 +MetaTest/__unnamed_task__/AverageReturn -51.1091 +MetaTest/__unnamed_task__/Iteration 332 +MetaTest/__unnamed_task__/MaxReturn -44.34 +MetaTest/__unnamed_task__/MinReturn -65.4998 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.47079 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.5984e+07 +__unnamed_task__/AverageDiscountedReturn -28.3426 +__unnamed_task__/AverageReturn -50.6164 +__unnamed_task__/Iteration 332 +__unnamed_task__/MaxReturn -43.4737 +__unnamed_task__/MinReturn -69.6072 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.74619 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 07:11:27 | [maml_trainer] epoch #333 | Sampling for adapation and meta-testing... +2025-04-10 07:15:19 | [maml_trainer] epoch #333 | Finished meta-testing... +2025-04-10 07:15:19 | [maml_trainer] epoch #333 | Saving snapshot... +2025-04-10 07:15:40 | [maml_trainer] epoch #333 | Saved +2025-04-10 07:15:40 | [maml_trainer] epoch #333 | Time 570984.76 s +2025-04-10 07:15:40 | [maml_trainer] epoch #333 | EpochTime 1652.59 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.9262 +Average/AverageReturn -49.3443 +Average/Iteration 333 +Average/MaxReturn -41.203 +Average/MinReturn -63.0138 +Average/NumEpisodes 120 +Average/StdReturn 4.37436 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.79041 +GaussianMLPPolicy/KLAfter 0.00377982 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.88489e-05 +GaussianMLPPolicy/LossBefore -2.06629e-09 +GaussianMLPPolicy/dLoss -4.8851e-05 +Iteration 333 +MetaTest/Average/AverageDiscountedReturn -49.8123 +MetaTest/Average/AverageReturn -49.8123 +MetaTest/Average/Iteration 333 +MetaTest/Average/MaxReturn -44.5652 +MetaTest/Average/MinReturn -59.6028 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.31855 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8123 +MetaTest/__unnamed_task__/AverageReturn -49.8123 +MetaTest/__unnamed_task__/Iteration 333 +MetaTest/__unnamed_task__/MaxReturn -44.5652 +MetaTest/__unnamed_task__/MinReturn -59.6028 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.31855 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6032e+07 +__unnamed_task__/AverageDiscountedReturn -27.9262 +__unnamed_task__/AverageReturn -49.3443 +__unnamed_task__/Iteration 333 +__unnamed_task__/MaxReturn -41.203 +__unnamed_task__/MinReturn -63.0138 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.37436 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 07:39:08 | [maml_trainer] epoch #334 | Sampling for adapation and meta-testing... +2025-04-10 07:43:02 | [maml_trainer] epoch #334 | Finished meta-testing... +2025-04-10 07:43:02 | [maml_trainer] epoch #334 | Saving snapshot... +2025-04-10 07:43:23 | [maml_trainer] epoch #334 | Saved +2025-04-10 07:43:23 | [maml_trainer] epoch #334 | Time 572647.57 s +2025-04-10 07:43:23 | [maml_trainer] epoch #334 | EpochTime 1662.80 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.822 +Average/AverageReturn -49.7049 +Average/Iteration 334 +Average/MaxReturn -41.9628 +Average/MinReturn -67.413 +Average/NumEpisodes 120 +Average/StdReturn 4.34189 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78958 +GaussianMLPPolicy/KLAfter 0.00260069 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.67725e-05 +GaussianMLPPolicy/LossBefore 1.27157e-08 +GaussianMLPPolicy/dLoss 7.67852e-05 +Iteration 334 +MetaTest/Average/AverageDiscountedReturn -47.463 +MetaTest/Average/AverageReturn -47.463 +MetaTest/Average/Iteration 334 +MetaTest/Average/MaxReturn -38.7175 +MetaTest/Average/MinReturn -55.3572 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.08291 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.463 +MetaTest/__unnamed_task__/AverageReturn -47.463 +MetaTest/__unnamed_task__/Iteration 334 +MetaTest/__unnamed_task__/MaxReturn -38.7175 +MetaTest/__unnamed_task__/MinReturn -55.3572 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.08291 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.608e+07 +__unnamed_task__/AverageDiscountedReturn -27.822 +__unnamed_task__/AverageReturn -49.7049 +__unnamed_task__/Iteration 334 +__unnamed_task__/MaxReturn -41.9628 +__unnamed_task__/MinReturn -67.413 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.34189 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 08:07:09 | [maml_trainer] epoch #335 | Sampling for adapation and meta-testing... +2025-04-10 08:11:02 | [maml_trainer] epoch #335 | Finished meta-testing... +2025-04-10 08:11:02 | [maml_trainer] epoch #335 | Saving snapshot... +2025-04-10 08:11:23 | [maml_trainer] epoch #335 | Saved +2025-04-10 08:11:23 | [maml_trainer] epoch #335 | Time 574327.04 s +2025-04-10 08:11:23 | [maml_trainer] epoch #335 | EpochTime 1679.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8024 +Average/AverageReturn -49.4923 +Average/Iteration 335 +Average/MaxReturn -42.489 +Average/MinReturn -64.1202 +Average/NumEpisodes 120 +Average/StdReturn 4.13721 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78875 +GaussianMLPPolicy/KLAfter 0.00391874 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.91936e-05 +GaussianMLPPolicy/LossBefore -1.85172e-08 +GaussianMLPPolicy/dLoss -6.92122e-05 +Iteration 335 +MetaTest/Average/AverageDiscountedReturn -48.4308 +MetaTest/Average/AverageReturn -48.4308 +MetaTest/Average/Iteration 335 +MetaTest/Average/MaxReturn -40.9707 +MetaTest/Average/MinReturn -57.7171 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.27567 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.4308 +MetaTest/__unnamed_task__/AverageReturn -48.4308 +MetaTest/__unnamed_task__/Iteration 335 +MetaTest/__unnamed_task__/MaxReturn -40.9707 +MetaTest/__unnamed_task__/MinReturn -57.7171 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.27567 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6128e+07 +__unnamed_task__/AverageDiscountedReturn -27.8024 +__unnamed_task__/AverageReturn -49.4923 +__unnamed_task__/Iteration 335 +__unnamed_task__/MaxReturn -42.489 +__unnamed_task__/MinReturn -64.1202 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.13721 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 08:34:55 | [maml_trainer] epoch #336 | Sampling for adapation and meta-testing... +2025-04-10 08:38:49 | [maml_trainer] epoch #336 | Finished meta-testing... +2025-04-10 08:38:49 | [maml_trainer] epoch #336 | Saving snapshot... +2025-04-10 08:39:10 | [maml_trainer] epoch #336 | Saved +2025-04-10 08:39:10 | [maml_trainer] epoch #336 | Time 575994.55 s +2025-04-10 08:39:10 | [maml_trainer] epoch #336 | EpochTime 1667.51 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.6179 +Average/AverageReturn -49.2039 +Average/Iteration 336 +Average/MaxReturn -42.3664 +Average/MinReturn -63.0145 +Average/NumEpisodes 120 +Average/StdReturn 4.15857 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78775 +GaussianMLPPolicy/KLAfter 0.00542487 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.41526e-05 +GaussianMLPPolicy/LossBefore 1.1007e-08 +GaussianMLPPolicy/dLoss 3.41636e-05 +Iteration 336 +MetaTest/Average/AverageDiscountedReturn -51.2222 +MetaTest/Average/AverageReturn -51.2222 +MetaTest/Average/Iteration 336 +MetaTest/Average/MaxReturn -44.0734 +MetaTest/Average/MinReturn -58.471 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.62711 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2222 +MetaTest/__unnamed_task__/AverageReturn -51.2222 +MetaTest/__unnamed_task__/Iteration 336 +MetaTest/__unnamed_task__/MaxReturn -44.0734 +MetaTest/__unnamed_task__/MinReturn -58.471 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.62711 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6176e+07 +__unnamed_task__/AverageDiscountedReturn -27.6179 +__unnamed_task__/AverageReturn -49.2039 +__unnamed_task__/Iteration 336 +__unnamed_task__/MaxReturn -42.3664 +__unnamed_task__/MinReturn -63.0145 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.15857 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 09:02:31 | [maml_trainer] epoch #337 | Sampling for adapation and meta-testing... +2025-04-10 09:06:28 | [maml_trainer] epoch #337 | Finished meta-testing... +2025-04-10 09:06:28 | [maml_trainer] epoch #337 | Saving snapshot... +2025-04-10 09:06:49 | [maml_trainer] epoch #337 | Saved +2025-04-10 09:06:49 | [maml_trainer] epoch #337 | Time 577653.81 s +2025-04-10 09:06:49 | [maml_trainer] epoch #337 | EpochTime 1659.26 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.5145 +Average/AverageReturn -48.5155 +Average/Iteration 337 +Average/MaxReturn -41.0935 +Average/MinReturn -68.3906 +Average/NumEpisodes 120 +Average/StdReturn 4.55022 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7863 +GaussianMLPPolicy/KLAfter 0.00237572 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000101747 +GaussianMLPPolicy/LossBefore -3.13918e-09 +GaussianMLPPolicy/dLoss 0.000101743 +Iteration 337 +MetaTest/Average/AverageDiscountedReturn -45.7733 +MetaTest/Average/AverageReturn -45.7733 +MetaTest/Average/Iteration 337 +MetaTest/Average/MaxReturn -40.4649 +MetaTest/Average/MinReturn -55.5923 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.79776 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.7733 +MetaTest/__unnamed_task__/AverageReturn -45.7733 +MetaTest/__unnamed_task__/Iteration 337 +MetaTest/__unnamed_task__/MaxReturn -40.4649 +MetaTest/__unnamed_task__/MinReturn -55.5923 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.79776 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6224e+07 +__unnamed_task__/AverageDiscountedReturn -27.5145 +__unnamed_task__/AverageReturn -48.5155 +__unnamed_task__/Iteration 337 +__unnamed_task__/MaxReturn -41.0935 +__unnamed_task__/MinReturn -68.3906 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.55022 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 09:30:30 | [maml_trainer] epoch #338 | Sampling for adapation and meta-testing... +2025-04-10 09:34:22 | [maml_trainer] epoch #338 | Finished meta-testing... +2025-04-10 09:34:22 | [maml_trainer] epoch #338 | Saving snapshot... +2025-04-10 09:34:43 | [maml_trainer] epoch #338 | Saved +2025-04-10 09:34:43 | [maml_trainer] epoch #338 | Time 579327.49 s +2025-04-10 09:34:43 | [maml_trainer] epoch #338 | EpochTime 1673.67 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.8596 +Average/AverageReturn -49.571 +Average/Iteration 338 +Average/MaxReturn -41.5215 +Average/MinReturn -91.0577 +Average/NumEpisodes 120 +Average/StdReturn 6.05628 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78479 +GaussianMLPPolicy/KLAfter 0.0026097 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.65436e-05 +GaussianMLPPolicy/LossBefore -5.5631e-09 +GaussianMLPPolicy/dLoss -3.65492e-05 +Iteration 338 +MetaTest/Average/AverageDiscountedReturn -48.1693 +MetaTest/Average/AverageReturn -48.1693 +MetaTest/Average/Iteration 338 +MetaTest/Average/MaxReturn -43.0881 +MetaTest/Average/MinReturn -54.6262 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.56521 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1693 +MetaTest/__unnamed_task__/AverageReturn -48.1693 +MetaTest/__unnamed_task__/Iteration 338 +MetaTest/__unnamed_task__/MaxReturn -43.0881 +MetaTest/__unnamed_task__/MinReturn -54.6262 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.56521 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6272e+07 +__unnamed_task__/AverageDiscountedReturn -27.8596 +__unnamed_task__/AverageReturn -49.571 +__unnamed_task__/Iteration 338 +__unnamed_task__/MaxReturn -41.5215 +__unnamed_task__/MinReturn -91.0577 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.05628 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 09:57:57 | [maml_trainer] epoch #339 | Sampling for adapation and meta-testing... +2025-04-10 10:01:51 | [maml_trainer] epoch #339 | Finished meta-testing... +2025-04-10 10:01:51 | [maml_trainer] epoch #339 | Saving snapshot... +2025-04-10 10:02:12 | [maml_trainer] epoch #339 | Saved +2025-04-10 10:02:12 | [maml_trainer] epoch #339 | Time 580976.34 s +2025-04-10 10:02:12 | [maml_trainer] epoch #339 | EpochTime 1648.85 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2203 +Average/AverageReturn -47.7864 +Average/Iteration 339 +Average/MaxReturn -40.7535 +Average/MinReturn -60.7291 +Average/NumEpisodes 120 +Average/StdReturn 4.40551 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7828 +GaussianMLPPolicy/KLAfter 0.00254717 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.69165e-05 +GaussianMLPPolicy/LossBefore 1.0848e-08 +GaussianMLPPolicy/dLoss -3.69057e-05 +Iteration 339 +MetaTest/Average/AverageDiscountedReturn -48.2726 +MetaTest/Average/AverageReturn -48.2726 +MetaTest/Average/Iteration 339 +MetaTest/Average/MaxReturn -42.5993 +MetaTest/Average/MinReturn -54.4183 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.86496 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2726 +MetaTest/__unnamed_task__/AverageReturn -48.2726 +MetaTest/__unnamed_task__/Iteration 339 +MetaTest/__unnamed_task__/MaxReturn -42.5993 +MetaTest/__unnamed_task__/MinReturn -54.4183 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.86496 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.632e+07 +__unnamed_task__/AverageDiscountedReturn -27.2203 +__unnamed_task__/AverageReturn -47.7864 +__unnamed_task__/Iteration 339 +__unnamed_task__/MaxReturn -40.7535 +__unnamed_task__/MinReturn -60.7291 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.40551 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 10:25:45 | [maml_trainer] epoch #340 | Sampling for adapation and meta-testing... +2025-04-10 10:29:42 | [maml_trainer] epoch #340 | Finished meta-testing... +2025-04-10 10:29:42 | [maml_trainer] epoch #340 | Saving snapshot... +2025-04-10 10:30:04 | [maml_trainer] epoch #340 | Saved +2025-04-10 10:30:04 | [maml_trainer] epoch #340 | Time 582648.04 s +2025-04-10 10:30:04 | [maml_trainer] epoch #340 | EpochTime 1671.70 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.1036 +Average/AverageReturn -48.1035 +Average/Iteration 340 +Average/MaxReturn -18.2123 +Average/MinReturn -104.007 +Average/NumEpisodes 120 +Average/StdReturn 7.88071 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.78079 +GaussianMLPPolicy/KLAfter 0.00440122 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.4764e-05 +GaussianMLPPolicy/LossBefore -5.64257e-09 +GaussianMLPPolicy/dLoss 2.47584e-05 +Iteration 340 +MetaTest/Average/AverageDiscountedReturn -48.204 +MetaTest/Average/AverageReturn -48.204 +MetaTest/Average/Iteration 340 +MetaTest/Average/MaxReturn -41.4605 +MetaTest/Average/MinReturn -58.866 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.1114 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.204 +MetaTest/__unnamed_task__/AverageReturn -48.204 +MetaTest/__unnamed_task__/Iteration 340 +MetaTest/__unnamed_task__/MaxReturn -41.4605 +MetaTest/__unnamed_task__/MinReturn -58.866 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.1114 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6368e+07 +__unnamed_task__/AverageDiscountedReturn -27.1036 +__unnamed_task__/AverageReturn -48.1035 +__unnamed_task__/Iteration 340 +__unnamed_task__/MaxReturn -18.2123 +__unnamed_task__/MinReturn -104.007 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.88071 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 10:53:49 | [maml_trainer] epoch #341 | Sampling for adapation and meta-testing... +2025-04-10 10:57:48 | [maml_trainer] epoch #341 | Finished meta-testing... +2025-04-10 10:57:48 | [maml_trainer] epoch #341 | Saving snapshot... +2025-04-10 10:58:10 | [maml_trainer] epoch #341 | Saved +2025-04-10 10:58:10 | [maml_trainer] epoch #341 | Time 584334.01 s +2025-04-10 10:58:10 | [maml_trainer] epoch #341 | EpochTime 1685.96 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8224 +Average/AverageReturn -46.2784 +Average/Iteration 341 +Average/MaxReturn 260.167 +Average/MinReturn -160.594 +Average/NumEpisodes 120 +Average/StdReturn 30.4718 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77972 +GaussianMLPPolicy/KLAfter 0.00314349 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.50273e-05 +GaussianMLPPolicy/LossBefore -4.07795e-09 +GaussianMLPPolicy/dLoss -1.50314e-05 +Iteration 341 +MetaTest/Average/AverageDiscountedReturn -46.0123 +MetaTest/Average/AverageReturn -46.0123 +MetaTest/Average/Iteration 341 +MetaTest/Average/MaxReturn -41.5247 +MetaTest/Average/MinReturn -52.6271 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.35698 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.0123 +MetaTest/__unnamed_task__/AverageReturn -46.0123 +MetaTest/__unnamed_task__/Iteration 341 +MetaTest/__unnamed_task__/MaxReturn -41.5247 +MetaTest/__unnamed_task__/MinReturn -52.6271 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.35698 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6416e+07 +__unnamed_task__/AverageDiscountedReturn -26.8224 +__unnamed_task__/AverageReturn -46.2784 +__unnamed_task__/Iteration 341 +__unnamed_task__/MaxReturn 260.167 +__unnamed_task__/MinReturn -160.594 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 30.4718 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 11:21:44 | [maml_trainer] epoch #342 | Sampling for adapation and meta-testing... +2025-04-10 11:25:41 | [maml_trainer] epoch #342 | Finished meta-testing... +2025-04-10 11:25:41 | [maml_trainer] epoch #342 | Saving snapshot... +2025-04-10 11:26:03 | [maml_trainer] epoch #342 | Saved +2025-04-10 11:26:03 | [maml_trainer] epoch #342 | Time 586007.93 s +2025-04-10 11:26:03 | [maml_trainer] epoch #342 | EpochTime 1673.92 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8311 +Average/AverageReturn -48.53 +Average/Iteration 342 +Average/MaxReturn -34.4779 +Average/MinReturn -122.396 +Average/NumEpisodes 120 +Average/StdReturn 11.5824 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77931 +GaussianMLPPolicy/KLAfter 0.00334503 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.34233e-05 +GaussianMLPPolicy/LossBefore 4.84784e-09 +GaussianMLPPolicy/dLoss 8.34281e-05 +Iteration 342 +MetaTest/Average/AverageDiscountedReturn -56.6738 +MetaTest/Average/AverageReturn -56.6738 +MetaTest/Average/Iteration 342 +MetaTest/Average/MaxReturn -39.0753 +MetaTest/Average/MinReturn -168.915 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 35.5374 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.6738 +MetaTest/__unnamed_task__/AverageReturn -56.6738 +MetaTest/__unnamed_task__/Iteration 342 +MetaTest/__unnamed_task__/MaxReturn -39.0753 +MetaTest/__unnamed_task__/MinReturn -168.915 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 35.5374 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6464e+07 +__unnamed_task__/AverageDiscountedReturn -26.8311 +__unnamed_task__/AverageReturn -48.53 +__unnamed_task__/Iteration 342 +__unnamed_task__/MaxReturn -34.4779 +__unnamed_task__/MinReturn -122.396 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.5824 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 11:49:55 | [maml_trainer] epoch #343 | Sampling for adapation and meta-testing... +2025-04-10 11:53:53 | [maml_trainer] epoch #343 | Finished meta-testing... +2025-04-10 11:53:53 | [maml_trainer] epoch #343 | Saving snapshot... +2025-04-10 11:54:14 | [maml_trainer] epoch #343 | Saved +2025-04-10 11:54:14 | [maml_trainer] epoch #343 | Time 587698.49 s +2025-04-10 11:54:14 | [maml_trainer] epoch #343 | EpochTime 1690.56 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.3684 +Average/AverageReturn -45.3781 +Average/Iteration 343 +Average/MaxReturn 236.89 +Average/MinReturn -92.2394 +Average/NumEpisodes 120 +Average/StdReturn 26.7517 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77893 +GaussianMLPPolicy/KLAfter 0.00340214 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.17932e-05 +GaussianMLPPolicy/LossBefore 5.5333e-09 +GaussianMLPPolicy/dLoss -5.17877e-05 +Iteration 343 +MetaTest/Average/AverageDiscountedReturn -45.8721 +MetaTest/Average/AverageReturn -45.8721 +MetaTest/Average/Iteration 343 +MetaTest/Average/MaxReturn -38.3481 +MetaTest/Average/MinReturn -57.021 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.07325 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8721 +MetaTest/__unnamed_task__/AverageReturn -45.8721 +MetaTest/__unnamed_task__/Iteration 343 +MetaTest/__unnamed_task__/MaxReturn -38.3481 +MetaTest/__unnamed_task__/MinReturn -57.021 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.07325 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6512e+07 +__unnamed_task__/AverageDiscountedReturn -26.3684 +__unnamed_task__/AverageReturn -45.3781 +__unnamed_task__/Iteration 343 +__unnamed_task__/MaxReturn 236.89 +__unnamed_task__/MinReturn -92.2394 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.7517 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 12:18:06 | [maml_trainer] epoch #344 | Sampling for adapation and meta-testing... +2025-04-10 12:22:01 | [maml_trainer] epoch #344 | Finished meta-testing... +2025-04-10 12:22:01 | [maml_trainer] epoch #344 | Saving snapshot... +2025-04-10 12:22:21 | [maml_trainer] epoch #344 | Saved +2025-04-10 12:22:21 | [maml_trainer] epoch #344 | Time 589385.73 s +2025-04-10 12:22:21 | [maml_trainer] epoch #344 | EpochTime 1687.23 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.8145 +Average/AverageReturn -42.8209 +Average/Iteration 344 +Average/MaxReturn 491.186 +Average/MinReturn -85.8103 +Average/NumEpisodes 120 +Average/StdReturn 49.2876 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77872 +GaussianMLPPolicy/KLAfter 0.00323322 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.3822e-05 +GaussianMLPPolicy/LossBefore 5.33462e-09 +GaussianMLPPolicy/dLoss -4.38166e-05 +Iteration 344 +MetaTest/Average/AverageDiscountedReturn -55.0689 +MetaTest/Average/AverageReturn -55.0689 +MetaTest/Average/Iteration 344 +MetaTest/Average/MaxReturn -39.3562 +MetaTest/Average/MinReturn -135.411 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 24.8209 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.0689 +MetaTest/__unnamed_task__/AverageReturn -55.0689 +MetaTest/__unnamed_task__/Iteration 344 +MetaTest/__unnamed_task__/MaxReturn -39.3562 +MetaTest/__unnamed_task__/MinReturn -135.411 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 24.8209 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.656e+07 +__unnamed_task__/AverageDiscountedReturn -25.8145 +__unnamed_task__/AverageReturn -42.8209 +__unnamed_task__/Iteration 344 +__unnamed_task__/MaxReturn 491.186 +__unnamed_task__/MinReturn -85.8103 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 49.2876 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 12:46:11 | [maml_trainer] epoch #345 | Sampling for adapation and meta-testing... +2025-04-10 12:50:11 | [maml_trainer] epoch #345 | Finished meta-testing... +2025-04-10 12:50:11 | [maml_trainer] epoch #345 | Saving snapshot... +2025-04-10 12:50:32 | [maml_trainer] epoch #345 | Saved +2025-04-10 12:50:32 | [maml_trainer] epoch #345 | Time 591076.57 s +2025-04-10 12:50:32 | [maml_trainer] epoch #345 | EpochTime 1690.84 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.9055 +Average/AverageReturn -42.0682 +Average/Iteration 345 +Average/MaxReturn 506.995 +Average/MinReturn -156.581 +Average/NumEpisodes 120 +Average/StdReturn 56.7 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77895 +GaussianMLPPolicy/KLAfter 0.002108 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.29349e-06 +GaussianMLPPolicy/LossBefore -6.45717e-11 +GaussianMLPPolicy/dLoss 3.29342e-06 +Iteration 345 +MetaTest/Average/AverageDiscountedReturn -17.4364 +MetaTest/Average/AverageReturn -17.4364 +MetaTest/Average/Iteration 345 +MetaTest/Average/MaxReturn 530.547 +MetaTest/Average/MinReturn -54.5433 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 125.794 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -17.4364 +MetaTest/__unnamed_task__/AverageReturn -17.4364 +MetaTest/__unnamed_task__/Iteration 345 +MetaTest/__unnamed_task__/MaxReturn 530.547 +MetaTest/__unnamed_task__/MinReturn -54.5433 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 125.794 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6608e+07 +__unnamed_task__/AverageDiscountedReturn -25.9055 +__unnamed_task__/AverageReturn -42.0682 +__unnamed_task__/Iteration 345 +__unnamed_task__/MaxReturn 506.995 +__unnamed_task__/MinReturn -156.581 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 56.7 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 13:14:26 | [maml_trainer] epoch #346 | Sampling for adapation and meta-testing... +2025-04-10 13:18:21 | [maml_trainer] epoch #346 | Finished meta-testing... +2025-04-10 13:18:21 | [maml_trainer] epoch #346 | Saving snapshot... +2025-04-10 13:18:42 | [maml_trainer] epoch #346 | Saved +2025-04-10 13:18:42 | [maml_trainer] epoch #346 | Time 592766.60 s +2025-04-10 13:18:42 | [maml_trainer] epoch #346 | EpochTime 1690.02 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.3529 +Average/AverageReturn -51.7625 +Average/Iteration 346 +Average/MaxReturn 92.2934 +Average/MinReturn -175.713 +Average/NumEpisodes 120 +Average/StdReturn 27.0521 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77941 +GaussianMLPPolicy/KLAfter 0.00288958 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.09317e-05 +GaussianMLPPolicy/LossBefore 3.47694e-09 +GaussianMLPPolicy/dLoss 6.09352e-05 +Iteration 346 +MetaTest/Average/AverageDiscountedReturn -56.4182 +MetaTest/Average/AverageReturn -56.4182 +MetaTest/Average/Iteration 346 +MetaTest/Average/MaxReturn -39.679 +MetaTest/Average/MinReturn -141.64 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 27.3489 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -56.4182 +MetaTest/__unnamed_task__/AverageReturn -56.4182 +MetaTest/__unnamed_task__/Iteration 346 +MetaTest/__unnamed_task__/MaxReturn -39.679 +MetaTest/__unnamed_task__/MinReturn -141.64 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 27.3489 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6656e+07 +__unnamed_task__/AverageDiscountedReturn -27.3529 +__unnamed_task__/AverageReturn -51.7625 +__unnamed_task__/Iteration 346 +__unnamed_task__/MaxReturn 92.2934 +__unnamed_task__/MinReturn -175.713 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 27.0521 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 13:42:28 | [maml_trainer] epoch #347 | Sampling for adapation and meta-testing... +2025-04-10 13:46:30 | [maml_trainer] epoch #347 | Finished meta-testing... +2025-04-10 13:46:30 | [maml_trainer] epoch #347 | Saving snapshot... +2025-04-10 13:46:51 | [maml_trainer] epoch #347 | Saved +2025-04-10 13:46:51 | [maml_trainer] epoch #347 | Time 594455.89 s +2025-04-10 13:46:51 | [maml_trainer] epoch #347 | EpochTime 1689.29 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.6368 +Average/AverageReturn -47.7993 +Average/Iteration 347 +Average/MaxReturn 265.471 +Average/MinReturn -171.585 +Average/NumEpisodes 120 +Average/StdReturn 33.785 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7795 +GaussianMLPPolicy/KLAfter 0.0023891 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.75993e-06 +GaussianMLPPolicy/LossBefore -4.91738e-10 +GaussianMLPPolicy/dLoss 5.75944e-06 +Iteration 347 +MetaTest/Average/AverageDiscountedReturn -47.1089 +MetaTest/Average/AverageReturn -47.1089 +MetaTest/Average/Iteration 347 +MetaTest/Average/MaxReturn -37.9657 +MetaTest/Average/MinReturn -68.8369 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.69524 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.1089 +MetaTest/__unnamed_task__/AverageReturn -47.1089 +MetaTest/__unnamed_task__/Iteration 347 +MetaTest/__unnamed_task__/MaxReturn -37.9657 +MetaTest/__unnamed_task__/MinReturn -68.8369 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.69524 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6704e+07 +__unnamed_task__/AverageDiscountedReturn -26.6368 +__unnamed_task__/AverageReturn -47.7993 +__unnamed_task__/Iteration 347 +__unnamed_task__/MaxReturn 265.471 +__unnamed_task__/MinReturn -171.585 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 33.785 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 14:10:55 | [maml_trainer] epoch #348 | Sampling for adapation and meta-testing... +2025-04-10 14:14:55 | [maml_trainer] epoch #348 | Finished meta-testing... +2025-04-10 14:14:55 | [maml_trainer] epoch #348 | Saving snapshot... +2025-04-10 14:15:16 | [maml_trainer] epoch #348 | Saved +2025-04-10 14:15:16 | [maml_trainer] epoch #348 | Time 596160.76 s +2025-04-10 14:15:16 | [maml_trainer] epoch #348 | EpochTime 1704.87 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.5447 +Average/AverageReturn -48.5559 +Average/Iteration 348 +Average/MaxReturn -30.7952 +Average/MinReturn -83.7109 +Average/NumEpisodes 120 +Average/StdReturn 8.53471 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77867 +GaussianMLPPolicy/KLAfter 0.00140346 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.40921e-06 +GaussianMLPPolicy/LossBefore -2.3524e-08 +GaussianMLPPolicy/dLoss -1.43274e-06 +Iteration 348 +MetaTest/Average/AverageDiscountedReturn -58.244 +MetaTest/Average/AverageReturn -58.244 +MetaTest/Average/Iteration 348 +MetaTest/Average/MaxReturn 44.5969 +MetaTest/Average/MinReturn -171.857 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 43.8402 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.244 +MetaTest/__unnamed_task__/AverageReturn -58.244 +MetaTest/__unnamed_task__/Iteration 348 +MetaTest/__unnamed_task__/MaxReturn 44.5969 +MetaTest/__unnamed_task__/MinReturn -171.857 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 43.8402 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6752e+07 +__unnamed_task__/AverageDiscountedReturn -26.5447 +__unnamed_task__/AverageReturn -48.5559 +__unnamed_task__/Iteration 348 +__unnamed_task__/MaxReturn -30.7952 +__unnamed_task__/MinReturn -83.7109 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.53471 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 14:39:19 | [maml_trainer] epoch #349 | Sampling for adapation and meta-testing... +2025-04-10 14:43:19 | [maml_trainer] epoch #349 | Finished meta-testing... +2025-04-10 14:43:19 | [maml_trainer] epoch #349 | Saving snapshot... +2025-04-10 14:43:40 | [maml_trainer] epoch #349 | Saved +2025-04-10 14:43:40 | [maml_trainer] epoch #349 | Time 597864.19 s +2025-04-10 14:43:40 | [maml_trainer] epoch #349 | EpochTime 1703.42 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.3248 +Average/AverageReturn -46.8097 +Average/Iteration 349 +Average/MaxReturn 554.352 +Average/MinReturn -163.407 +Average/NumEpisodes 120 +Average/StdReturn 59.0897 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77799 +GaussianMLPPolicy/KLAfter 0.00144969 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.80586e-05 +GaussianMLPPolicy/LossBefore 3.41733e-09 +GaussianMLPPolicy/dLoss 2.8062e-05 +Iteration 349 +MetaTest/Average/AverageDiscountedReturn -47.9453 +MetaTest/Average/AverageReturn -47.9453 +MetaTest/Average/Iteration 349 +MetaTest/Average/MaxReturn -42.88 +MetaTest/Average/MinReturn -60.8222 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.92229 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.9453 +MetaTest/__unnamed_task__/AverageReturn -47.9453 +MetaTest/__unnamed_task__/Iteration 349 +MetaTest/__unnamed_task__/MaxReturn -42.88 +MetaTest/__unnamed_task__/MinReturn -60.8222 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.92229 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.68e+07 +__unnamed_task__/AverageDiscountedReturn -26.3248 +__unnamed_task__/AverageReturn -46.8097 +__unnamed_task__/Iteration 349 +__unnamed_task__/MaxReturn 554.352 +__unnamed_task__/MinReturn -163.407 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 59.0897 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 15:07:37 | [maml_trainer] epoch #350 | Sampling for adapation and meta-testing... +2025-04-10 15:11:39 | [maml_trainer] epoch #350 | Finished meta-testing... +2025-04-10 15:11:39 | [maml_trainer] epoch #350 | Saving snapshot... +2025-04-10 15:12:00 | [maml_trainer] epoch #350 | Saved +2025-04-10 15:12:00 | [maml_trainer] epoch #350 | Time 599564.81 s +2025-04-10 15:12:00 | [maml_trainer] epoch #350 | EpochTime 1700.62 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.0338 +Average/AverageReturn -45.8953 +Average/Iteration 350 +Average/MaxReturn 315.648 +Average/MinReturn -164.983 +Average/NumEpisodes 120 +Average/StdReturn 38.3106 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77792 +GaussianMLPPolicy/KLAfter 0.00161964 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.26264e-05 +GaussianMLPPolicy/LossBefore -2.111e-09 +GaussianMLPPolicy/dLoss -2.26285e-05 +Iteration 350 +MetaTest/Average/AverageDiscountedReturn -46.8206 +MetaTest/Average/AverageReturn -46.8206 +MetaTest/Average/Iteration 350 +MetaTest/Average/MaxReturn -40.1742 +MetaTest/Average/MinReturn -54.8733 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.64404 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.8206 +MetaTest/__unnamed_task__/AverageReturn -46.8206 +MetaTest/__unnamed_task__/Iteration 350 +MetaTest/__unnamed_task__/MaxReturn -40.1742 +MetaTest/__unnamed_task__/MinReturn -54.8733 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.64404 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6848e+07 +__unnamed_task__/AverageDiscountedReturn -26.0338 +__unnamed_task__/AverageReturn -45.8953 +__unnamed_task__/Iteration 350 +__unnamed_task__/MaxReturn 315.648 +__unnamed_task__/MinReturn -164.983 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 38.3106 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 15:38:46 | [maml_trainer] epoch #351 | Sampling for adapation and meta-testing... +2025-04-10 15:44:29 | [maml_trainer] epoch #351 | Finished meta-testing... +2025-04-10 15:44:29 | [maml_trainer] epoch #351 | Saving snapshot... +2025-04-10 15:45:17 | [maml_trainer] epoch #351 | Saved +2025-04-10 15:45:17 | [maml_trainer] epoch #351 | Time 601561.62 s +2025-04-10 15:45:17 | [maml_trainer] epoch #351 | EpochTime 1996.80 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.7309 +Average/AverageReturn -49.0293 +Average/Iteration 351 +Average/MaxReturn -11.8491 +Average/MinReturn -135.071 +Average/NumEpisodes 120 +Average/StdReturn 11.9317 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77715 +GaussianMLPPolicy/KLAfter 0.00204304 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.84629e-05 +GaussianMLPPolicy/LossBefore 5.88099e-09 +GaussianMLPPolicy/dLoss 4.84688e-05 +Iteration 351 +MetaTest/Average/AverageDiscountedReturn -48.2335 +MetaTest/Average/AverageReturn -48.2335 +MetaTest/Average/Iteration 351 +MetaTest/Average/MaxReturn -42.2676 +MetaTest/Average/MinReturn -56.6558 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.51737 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2335 +MetaTest/__unnamed_task__/AverageReturn -48.2335 +MetaTest/__unnamed_task__/Iteration 351 +MetaTest/__unnamed_task__/MaxReturn -42.2676 +MetaTest/__unnamed_task__/MinReturn -56.6558 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.51737 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6896e+07 +__unnamed_task__/AverageDiscountedReturn -26.7309 +__unnamed_task__/AverageReturn -49.0293 +__unnamed_task__/Iteration 351 +__unnamed_task__/MaxReturn -11.8491 +__unnamed_task__/MinReturn -135.071 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.9317 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 17:05:27 | [maml_trainer] epoch #352 | Sampling for adapation and meta-testing... +2025-04-10 17:17:35 | [maml_trainer] epoch #352 | Finished meta-testing... +2025-04-10 17:17:35 | [maml_trainer] epoch #352 | Saving snapshot... +2025-04-10 17:18:57 | [maml_trainer] epoch #352 | Saved +2025-04-10 17:18:57 | [maml_trainer] epoch #352 | Time 607181.49 s +2025-04-10 17:18:57 | [maml_trainer] epoch #352 | EpochTime 5619.86 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.2693 +Average/AverageReturn -47.236 +Average/Iteration 352 +Average/MaxReturn -39.038 +Average/MinReturn -69.3008 +Average/NumEpisodes 120 +Average/StdReturn 4.95033 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77687 +GaussianMLPPolicy/KLAfter 0.00235526 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.16452e-06 +GaussianMLPPolicy/LossBefore -4.29154e-09 +GaussianMLPPolicy/dLoss -2.16881e-06 +Iteration 352 +MetaTest/Average/AverageDiscountedReturn -47.4036 +MetaTest/Average/AverageReturn -47.4036 +MetaTest/Average/Iteration 352 +MetaTest/Average/MaxReturn -41.8166 +MetaTest/Average/MinReturn -64.7987 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.33684 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4036 +MetaTest/__unnamed_task__/AverageReturn -47.4036 +MetaTest/__unnamed_task__/Iteration 352 +MetaTest/__unnamed_task__/MaxReturn -41.8166 +MetaTest/__unnamed_task__/MinReturn -64.7987 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.33684 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6944e+07 +__unnamed_task__/AverageDiscountedReturn -26.2693 +__unnamed_task__/AverageReturn -47.236 +__unnamed_task__/Iteration 352 +__unnamed_task__/MaxReturn -39.038 +__unnamed_task__/MinReturn -69.3008 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.95033 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 18:19:24 | [maml_trainer] epoch #353 | Sampling for adapation and meta-testing... +2025-04-10 18:29:15 | [maml_trainer] epoch #353 | Finished meta-testing... +2025-04-10 18:29:15 | [maml_trainer] epoch #353 | Saving snapshot... +2025-04-10 18:30:12 | [maml_trainer] epoch #353 | Saved +2025-04-10 18:30:12 | [maml_trainer] epoch #353 | Time 611456.96 s +2025-04-10 18:30:12 | [maml_trainer] epoch #353 | EpochTime 4275.45 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.2737 +Average/AverageReturn -47.1847 +Average/Iteration 353 +Average/MaxReturn -40.7602 +Average/MinReturn -64.4095 +Average/NumEpisodes 120 +Average/StdReturn 4.30525 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77606 +GaussianMLPPolicy/KLAfter 0.00305461 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.56491e-05 +GaussianMLPPolicy/LossBefore -5.00679e-09 +GaussianMLPPolicy/dLoss 4.56441e-05 +Iteration 353 +MetaTest/Average/AverageDiscountedReturn -49.6879 +MetaTest/Average/AverageReturn -49.6879 +MetaTest/Average/Iteration 353 +MetaTest/Average/MaxReturn -41.45 +MetaTest/Average/MinReturn -67.3536 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.88937 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6879 +MetaTest/__unnamed_task__/AverageReturn -49.6879 +MetaTest/__unnamed_task__/Iteration 353 +MetaTest/__unnamed_task__/MaxReturn -41.45 +MetaTest/__unnamed_task__/MinReturn -67.3536 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.88937 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.6992e+07 +__unnamed_task__/AverageDiscountedReturn -26.2737 +__unnamed_task__/AverageReturn -47.1847 +__unnamed_task__/Iteration 353 +__unnamed_task__/MaxReturn -40.7602 +__unnamed_task__/MinReturn -64.4095 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.30525 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 19:02:02 | [maml_trainer] epoch #354 | Sampling for adapation and meta-testing... +2025-04-10 19:06:01 | [maml_trainer] epoch #354 | Finished meta-testing... +2025-04-10 19:06:01 | [maml_trainer] epoch #354 | Saving snapshot... +2025-04-10 19:06:23 | [maml_trainer] epoch #354 | Saved +2025-04-10 19:06:23 | [maml_trainer] epoch #354 | Time 613627.39 s +2025-04-10 19:06:23 | [maml_trainer] epoch #354 | EpochTime 2170.43 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.445 +Average/AverageReturn -48.3626 +Average/Iteration 354 +Average/MaxReturn -38.5825 +Average/MinReturn -122.351 +Average/NumEpisodes 120 +Average/StdReturn 8.52376 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77416 +GaussianMLPPolicy/KLAfter 0.00250503 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.23035e-05 +GaussianMLPPolicy/LossBefore -6.0002e-09 +GaussianMLPPolicy/dLoss 3.22975e-05 +Iteration 354 +MetaTest/Average/AverageDiscountedReturn -46.662 +MetaTest/Average/AverageReturn -46.662 +MetaTest/Average/Iteration 354 +MetaTest/Average/MaxReturn -40.3315 +MetaTest/Average/MinReturn -60.1771 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.7498 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.662 +MetaTest/__unnamed_task__/AverageReturn -46.662 +MetaTest/__unnamed_task__/Iteration 354 +MetaTest/__unnamed_task__/MaxReturn -40.3315 +MetaTest/__unnamed_task__/MinReturn -60.1771 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.7498 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.704e+07 +__unnamed_task__/AverageDiscountedReturn -26.445 +__unnamed_task__/AverageReturn -48.3626 +__unnamed_task__/Iteration 354 +__unnamed_task__/MaxReturn -38.5825 +__unnamed_task__/MinReturn -122.351 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.52376 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 19:30:19 | [maml_trainer] epoch #355 | Sampling for adapation and meta-testing... +2025-04-10 19:34:21 | [maml_trainer] epoch #355 | Finished meta-testing... +2025-04-10 19:34:21 | [maml_trainer] epoch #355 | Saving snapshot... +2025-04-10 19:34:42 | [maml_trainer] epoch #355 | Saved +2025-04-10 19:34:42 | [maml_trainer] epoch #355 | Time 615326.42 s +2025-04-10 19:34:42 | [maml_trainer] epoch #355 | EpochTime 1699.03 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.8392 +Average/AverageReturn -48.5163 +Average/Iteration 355 +Average/MaxReturn -38.2182 +Average/MinReturn -65.7578 +Average/NumEpisodes 120 +Average/StdReturn 4.7003 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.77126 +GaussianMLPPolicy/KLAfter 0.00214973 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000112047 +GaussianMLPPolicy/LossBefore 1.11262e-08 +GaussianMLPPolicy/dLoss -0.000112036 +Iteration 355 +MetaTest/Average/AverageDiscountedReturn -47.2316 +MetaTest/Average/AverageReturn -47.2316 +MetaTest/Average/Iteration 355 +MetaTest/Average/MaxReturn -40.1521 +MetaTest/Average/MinReturn -52.0328 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.23378 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2316 +MetaTest/__unnamed_task__/AverageReturn -47.2316 +MetaTest/__unnamed_task__/Iteration 355 +MetaTest/__unnamed_task__/MaxReturn -40.1521 +MetaTest/__unnamed_task__/MinReturn -52.0328 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.23378 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7088e+07 +__unnamed_task__/AverageDiscountedReturn -26.8392 +__unnamed_task__/AverageReturn -48.5163 +__unnamed_task__/Iteration 355 +__unnamed_task__/MaxReturn -38.2182 +__unnamed_task__/MinReturn -65.7578 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.7003 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 19:58:53 | [maml_trainer] epoch #356 | Sampling for adapation and meta-testing... +2025-04-10 20:02:55 | [maml_trainer] epoch #356 | Finished meta-testing... +2025-04-10 20:02:55 | [maml_trainer] epoch #356 | Saving snapshot... +2025-04-10 20:03:17 | [maml_trainer] epoch #356 | Saved +2025-04-10 20:03:17 | [maml_trainer] epoch #356 | Time 617041.52 s +2025-04-10 20:03:17 | [maml_trainer] epoch #356 | EpochTime 1715.09 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.4275 +Average/AverageReturn -48.1462 +Average/Iteration 356 +Average/MaxReturn -39.8005 +Average/MinReturn -117.836 +Average/NumEpisodes 120 +Average/StdReturn 7.74874 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.76875 +GaussianMLPPolicy/KLAfter 0.00235676 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.74407e-05 +GaussianMLPPolicy/LossBefore -1.01725e-08 +GaussianMLPPolicy/dLoss 1.74305e-05 +Iteration 356 +MetaTest/Average/AverageDiscountedReturn -48.1991 +MetaTest/Average/AverageReturn -48.1991 +MetaTest/Average/Iteration 356 +MetaTest/Average/MaxReturn -40.7087 +MetaTest/Average/MinReturn -65.1649 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.12006 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1991 +MetaTest/__unnamed_task__/AverageReturn -48.1991 +MetaTest/__unnamed_task__/Iteration 356 +MetaTest/__unnamed_task__/MaxReturn -40.7087 +MetaTest/__unnamed_task__/MinReturn -65.1649 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.12006 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7136e+07 +__unnamed_task__/AverageDiscountedReturn -26.4275 +__unnamed_task__/AverageReturn -48.1462 +__unnamed_task__/Iteration 356 +__unnamed_task__/MaxReturn -39.8005 +__unnamed_task__/MinReturn -117.836 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.74874 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-10 20:27:25 | [maml_trainer] epoch #357 | Sampling for adapation and meta-testing... +2025-04-10 20:31:28 | [maml_trainer] epoch #357 | Finished meta-testing... +2025-04-10 20:31:28 | [maml_trainer] epoch #357 | Saving snapshot... +2025-04-10 20:31:50 | [maml_trainer] epoch #357 | Saved +2025-04-10 20:31:50 | [maml_trainer] epoch #357 | Time 618754.27 s +2025-04-10 20:31:50 | [maml_trainer] epoch #357 | EpochTime 1712.75 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.6459 +Average/AverageReturn -48.3248 +Average/Iteration 357 +Average/MaxReturn -39.2767 +Average/MinReturn -61.8611 +Average/NumEpisodes 120 +Average/StdReturn 4.44233 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.76566 +GaussianMLPPolicy/KLAfter 0.00201794 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.31376e-05 +GaussianMLPPolicy/LossBefore -6.03994e-09 +GaussianMLPPolicy/dLoss -2.31437e-05 +Iteration 357 +MetaTest/Average/AverageDiscountedReturn -54.1931 +MetaTest/Average/AverageReturn -54.1931 +MetaTest/Average/Iteration 357 +MetaTest/Average/MaxReturn -44.0156 +MetaTest/Average/MinReturn -95.1916 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.7912 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1931 +MetaTest/__unnamed_task__/AverageReturn -54.1931 +MetaTest/__unnamed_task__/Iteration 357 +MetaTest/__unnamed_task__/MaxReturn -44.0156 +MetaTest/__unnamed_task__/MinReturn -95.1916 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.7912 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7184e+07 +__unnamed_task__/AverageDiscountedReturn -26.6459 +__unnamed_task__/AverageReturn -48.3248 +__unnamed_task__/Iteration 357 +__unnamed_task__/MaxReturn -39.2767 +__unnamed_task__/MinReturn -61.8611 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.44233 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 20:55:49 | [maml_trainer] epoch #358 | Sampling for adapation and meta-testing... +2025-04-10 20:59:46 | [maml_trainer] epoch #358 | Finished meta-testing... +2025-04-10 20:59:46 | [maml_trainer] epoch #358 | Saving snapshot... +2025-04-10 21:00:07 | [maml_trainer] epoch #358 | Saved +2025-04-10 21:00:07 | [maml_trainer] epoch #358 | Time 620451.65 s +2025-04-10 21:00:07 | [maml_trainer] epoch #358 | EpochTime 1697.38 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.4594 +Average/AverageReturn -47.8378 +Average/Iteration 358 +Average/MaxReturn -39.7995 +Average/MinReturn -59.7202 +Average/NumEpisodes 120 +Average/StdReturn 4.02066 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.76232 +GaussianMLPPolicy/KLAfter 0.00155588 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.59632e-05 +GaussianMLPPolicy/LossBefore -7.15256e-10 +GaussianMLPPolicy/dLoss -4.59639e-05 +Iteration 358 +MetaTest/Average/AverageDiscountedReturn -48.8982 +MetaTest/Average/AverageReturn -48.8982 +MetaTest/Average/Iteration 358 +MetaTest/Average/MaxReturn -41.0996 +MetaTest/Average/MinReturn -58.1018 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.73285 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.8982 +MetaTest/__unnamed_task__/AverageReturn -48.8982 +MetaTest/__unnamed_task__/Iteration 358 +MetaTest/__unnamed_task__/MaxReturn -41.0996 +MetaTest/__unnamed_task__/MinReturn -58.1018 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.73285 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7232e+07 +__unnamed_task__/AverageDiscountedReturn -26.4594 +__unnamed_task__/AverageReturn -47.8378 +__unnamed_task__/Iteration 358 +__unnamed_task__/MaxReturn -39.7995 +__unnamed_task__/MinReturn -59.7202 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.02066 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 21:26:10 | [maml_trainer] epoch #359 | Sampling for adapation and meta-testing... +2025-04-10 21:34:20 | [maml_trainer] epoch #359 | Finished meta-testing... +2025-04-10 21:34:20 | [maml_trainer] epoch #359 | Saving snapshot... +2025-04-10 21:35:05 | [maml_trainer] epoch #359 | Saved +2025-04-10 21:35:05 | [maml_trainer] epoch #359 | Time 622549.48 s +2025-04-10 21:35:05 | [maml_trainer] epoch #359 | EpochTime 2097.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.5411 +Average/AverageReturn -48.1379 +Average/Iteration 359 +Average/MaxReturn -39.3972 +Average/MinReturn -64.3282 +Average/NumEpisodes 120 +Average/StdReturn 4.16013 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.75909 +GaussianMLPPolicy/KLAfter 0.00152738 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.33267e-05 +GaussianMLPPolicy/LossBefore 2.30471e-09 +GaussianMLPPolicy/dLoss -8.33244e-05 +Iteration 359 +MetaTest/Average/AverageDiscountedReturn -46.8195 +MetaTest/Average/AverageReturn -46.8195 +MetaTest/Average/Iteration 359 +MetaTest/Average/MaxReturn -43.4162 +MetaTest/Average/MinReturn -55.8563 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.30201 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.8195 +MetaTest/__unnamed_task__/AverageReturn -46.8195 +MetaTest/__unnamed_task__/Iteration 359 +MetaTest/__unnamed_task__/MaxReturn -43.4162 +MetaTest/__unnamed_task__/MinReturn -55.8563 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.30201 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.728e+07 +__unnamed_task__/AverageDiscountedReturn -26.5411 +__unnamed_task__/AverageReturn -48.1379 +__unnamed_task__/Iteration 359 +__unnamed_task__/MaxReturn -39.3972 +__unnamed_task__/MinReturn -64.3282 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.16013 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 22:19:03 | [maml_trainer] epoch #360 | Sampling for adapation and meta-testing... +2025-04-10 22:25:52 | [maml_trainer] epoch #360 | Finished meta-testing... +2025-04-10 22:25:52 | [maml_trainer] epoch #360 | Saving snapshot... +2025-04-10 22:26:30 | [maml_trainer] epoch #360 | Saved +2025-04-10 22:26:30 | [maml_trainer] epoch #360 | Time 625634.60 s +2025-04-10 22:26:30 | [maml_trainer] epoch #360 | EpochTime 3085.12 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.6566 +Average/AverageReturn -48.1194 +Average/Iteration 360 +Average/MaxReturn -33.1978 +Average/MinReturn -60.0951 +Average/NumEpisodes 120 +Average/StdReturn 4.01875 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.75694 +GaussianMLPPolicy/KLAfter 0.00178989 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.04404e-05 +GaussianMLPPolicy/LossBefore 1.10865e-08 +GaussianMLPPolicy/dLoss -9.04293e-05 +Iteration 360 +MetaTest/Average/AverageDiscountedReturn -50.0833 +MetaTest/Average/AverageReturn -50.0833 +MetaTest/Average/Iteration 360 +MetaTest/Average/MaxReturn -41.5464 +MetaTest/Average/MinReturn -79.142 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.0338 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0833 +MetaTest/__unnamed_task__/AverageReturn -50.0833 +MetaTest/__unnamed_task__/Iteration 360 +MetaTest/__unnamed_task__/MaxReturn -41.5464 +MetaTest/__unnamed_task__/MinReturn -79.142 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.0338 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7328e+07 +__unnamed_task__/AverageDiscountedReturn -26.6566 +__unnamed_task__/AverageReturn -48.1194 +__unnamed_task__/Iteration 360 +__unnamed_task__/MaxReturn -33.1978 +__unnamed_task__/MinReturn -60.0951 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.01875 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 23:07:17 | [maml_trainer] epoch #361 | Sampling for adapation and meta-testing... +2025-04-10 23:13:59 | [maml_trainer] epoch #361 | Finished meta-testing... +2025-04-10 23:13:59 | [maml_trainer] epoch #361 | Saving snapshot... +2025-04-10 23:14:35 | [maml_trainer] epoch #361 | Saved +2025-04-10 23:14:35 | [maml_trainer] epoch #361 | Time 628519.93 s +2025-04-10 23:14:35 | [maml_trainer] epoch #361 | EpochTime 2885.32 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.2684 +Average/AverageReturn -47.2216 +Average/Iteration 361 +Average/MaxReturn -40.5096 +Average/MinReturn -70.7171 +Average/NumEpisodes 120 +Average/StdReturn 4.45201 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.75369 +GaussianMLPPolicy/KLAfter 0.00110998 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.85357e-05 +GaussianMLPPolicy/LossBefore -8.5036e-09 +GaussianMLPPolicy/dLoss -3.85442e-05 +Iteration 361 +MetaTest/Average/AverageDiscountedReturn -48.7528 +MetaTest/Average/AverageReturn -48.7528 +MetaTest/Average/Iteration 361 +MetaTest/Average/MaxReturn -41.8007 +MetaTest/Average/MinReturn -56.5087 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.9291 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7528 +MetaTest/__unnamed_task__/AverageReturn -48.7528 +MetaTest/__unnamed_task__/Iteration 361 +MetaTest/__unnamed_task__/MaxReturn -41.8007 +MetaTest/__unnamed_task__/MinReturn -56.5087 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.9291 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7376e+07 +__unnamed_task__/AverageDiscountedReturn -26.2684 +__unnamed_task__/AverageReturn -47.2216 +__unnamed_task__/Iteration 361 +__unnamed_task__/MaxReturn -40.5096 +__unnamed_task__/MinReturn -70.7171 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.45201 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-10 23:55:14 | [maml_trainer] epoch #362 | Sampling for adapation and meta-testing... +2025-04-11 00:01:58 | [maml_trainer] epoch #362 | Finished meta-testing... +2025-04-11 00:01:58 | [maml_trainer] epoch #362 | Saving snapshot... +2025-04-11 00:02:35 | [maml_trainer] epoch #362 | Saved +2025-04-11 00:02:35 | [maml_trainer] epoch #362 | Time 631399.94 s +2025-04-11 00:02:35 | [maml_trainer] epoch #362 | EpochTime 2880.00 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.3635 +Average/AverageReturn -48.1188 +Average/Iteration 362 +Average/MaxReturn -40.3025 +Average/MinReturn -108.161 +Average/NumEpisodes 120 +Average/StdReturn 7.37844 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.75081 +GaussianMLPPolicy/KLAfter 0.000962979 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.22265e-05 +GaussianMLPPolicy/LossBefore -5.16574e-10 +GaussianMLPPolicy/dLoss 6.2226e-05 +Iteration 362 +MetaTest/Average/AverageDiscountedReturn -48.6433 +MetaTest/Average/AverageReturn -48.6433 +MetaTest/Average/Iteration 362 +MetaTest/Average/MaxReturn -41.4452 +MetaTest/Average/MinReturn -61.5311 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.70867 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6433 +MetaTest/__unnamed_task__/AverageReturn -48.6433 +MetaTest/__unnamed_task__/Iteration 362 +MetaTest/__unnamed_task__/MaxReturn -41.4452 +MetaTest/__unnamed_task__/MinReturn -61.5311 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.70867 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7424e+07 +__unnamed_task__/AverageDiscountedReturn -26.3635 +__unnamed_task__/AverageReturn -48.1188 +__unnamed_task__/Iteration 362 +__unnamed_task__/MaxReturn -40.3025 +__unnamed_task__/MinReturn -108.161 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.37844 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 00:43:05 | [maml_trainer] epoch #363 | Sampling for adapation and meta-testing... +2025-04-11 00:49:50 | [maml_trainer] epoch #363 | Finished meta-testing... +2025-04-11 00:49:50 | [maml_trainer] epoch #363 | Saving snapshot... +2025-04-11 00:50:26 | [maml_trainer] epoch #363 | Saved +2025-04-11 00:50:26 | [maml_trainer] epoch #363 | Time 634270.83 s +2025-04-11 00:50:26 | [maml_trainer] epoch #363 | EpochTime 2870.88 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.7352 +Average/AverageReturn -48.7336 +Average/Iteration 363 +Average/MaxReturn -38.994 +Average/MinReturn -102.472 +Average/NumEpisodes 120 +Average/StdReturn 7.50753 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.74754 +GaussianMLPPolicy/KLAfter 0.00236871 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.09847e-05 +GaussianMLPPolicy/LossBefore -9.45727e-09 +GaussianMLPPolicy/dLoss -7.09941e-05 +Iteration 363 +MetaTest/Average/AverageDiscountedReturn -48.503 +MetaTest/Average/AverageReturn -48.503 +MetaTest/Average/Iteration 363 +MetaTest/Average/MaxReturn -41.0585 +MetaTest/Average/MinReturn -58.0362 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.41657 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.503 +MetaTest/__unnamed_task__/AverageReturn -48.503 +MetaTest/__unnamed_task__/Iteration 363 +MetaTest/__unnamed_task__/MaxReturn -41.0585 +MetaTest/__unnamed_task__/MinReturn -58.0362 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.41657 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7472e+07 +__unnamed_task__/AverageDiscountedReturn -26.7352 +__unnamed_task__/AverageReturn -48.7336 +__unnamed_task__/Iteration 363 +__unnamed_task__/MaxReturn -38.994 +__unnamed_task__/MinReturn -102.472 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.50753 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 01:23:50 | [maml_trainer] epoch #364 | Sampling for adapation and meta-testing... +2025-04-11 01:27:56 | [maml_trainer] epoch #364 | Finished meta-testing... +2025-04-11 01:27:56 | [maml_trainer] epoch #364 | Saving snapshot... +2025-04-11 01:28:17 | [maml_trainer] epoch #364 | Saved +2025-04-11 01:28:17 | [maml_trainer] epoch #364 | Time 636541.69 s +2025-04-11 01:28:17 | [maml_trainer] epoch #364 | EpochTime 2270.86 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.4237 +Average/AverageReturn -47.4927 +Average/Iteration 364 +Average/MaxReturn -38.4012 +Average/MinReturn -58.5517 +Average/NumEpisodes 120 +Average/StdReturn 3.68562 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.74353 +GaussianMLPPolicy/KLAfter 0.00282592 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.86421e-05 +GaussianMLPPolicy/LossBefore 1.77224e-08 +GaussianMLPPolicy/dLoss -6.86243e-05 +Iteration 364 +MetaTest/Average/AverageDiscountedReturn -49.4552 +MetaTest/Average/AverageReturn -49.4552 +MetaTest/Average/Iteration 364 +MetaTest/Average/MaxReturn -44.5822 +MetaTest/Average/MinReturn -56.8331 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.4856 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.4552 +MetaTest/__unnamed_task__/AverageReturn -49.4552 +MetaTest/__unnamed_task__/Iteration 364 +MetaTest/__unnamed_task__/MaxReturn -44.5822 +MetaTest/__unnamed_task__/MinReturn -56.8331 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.4856 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.752e+07 +__unnamed_task__/AverageDiscountedReturn -26.4237 +__unnamed_task__/AverageReturn -47.4927 +__unnamed_task__/Iteration 364 +__unnamed_task__/MaxReturn -38.4012 +__unnamed_task__/MinReturn -58.5517 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 3.68562 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 01:52:18 | [maml_trainer] epoch #365 | Sampling for adapation and meta-testing... +2025-04-11 01:56:19 | [maml_trainer] epoch #365 | Finished meta-testing... +2025-04-11 01:56:19 | [maml_trainer] epoch #365 | Saving snapshot... +2025-04-11 01:56:40 | [maml_trainer] epoch #365 | Saved +2025-04-11 01:56:40 | [maml_trainer] epoch #365 | Time 638244.18 s +2025-04-11 01:56:40 | [maml_trainer] epoch #365 | EpochTime 1702.49 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.4331 +Average/AverageReturn -48.0583 +Average/Iteration 365 +Average/MaxReturn -40.648 +Average/MinReturn -109.88 +Average/NumEpisodes 120 +Average/StdReturn 6.89192 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.74028 +GaussianMLPPolicy/KLAfter 0.00160521 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.44893e-06 +GaussianMLPPolicy/LossBefore -7.70887e-09 +GaussianMLPPolicy/dLoss -4.45664e-06 +Iteration 365 +MetaTest/Average/AverageDiscountedReturn -50.0305 +MetaTest/Average/AverageReturn -50.0305 +MetaTest/Average/Iteration 365 +MetaTest/Average/MaxReturn -41.0323 +MetaTest/Average/MinReturn -67.6948 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.82818 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0305 +MetaTest/__unnamed_task__/AverageReturn -50.0305 +MetaTest/__unnamed_task__/Iteration 365 +MetaTest/__unnamed_task__/MaxReturn -41.0323 +MetaTest/__unnamed_task__/MinReturn -67.6948 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.82818 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7568e+07 +__unnamed_task__/AverageDiscountedReturn -26.4331 +__unnamed_task__/AverageReturn -48.0583 +__unnamed_task__/Iteration 365 +__unnamed_task__/MaxReturn -40.648 +__unnamed_task__/MinReturn -109.88 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.89192 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 02:20:32 | [maml_trainer] epoch #366 | Sampling for adapation and meta-testing... +2025-04-11 02:24:31 | [maml_trainer] epoch #366 | Finished meta-testing... +2025-04-11 02:24:31 | [maml_trainer] epoch #366 | Saving snapshot... +2025-04-11 02:24:53 | [maml_trainer] epoch #366 | Saved +2025-04-11 02:24:53 | [maml_trainer] epoch #366 | Time 639937.69 s +2025-04-11 02:24:53 | [maml_trainer] epoch #366 | EpochTime 1693.51 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.184 +Average/AverageReturn -47.2083 +Average/Iteration 366 +Average/MaxReturn -37.9778 +Average/MinReturn -59.8536 +Average/NumEpisodes 120 +Average/StdReturn 4.00732 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7382 +GaussianMLPPolicy/KLAfter 0.00111878 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.07023e-06 +GaussianMLPPolicy/LossBefore 1.04109e-08 +GaussianMLPPolicy/dLoss 8.08064e-06 +Iteration 366 +MetaTest/Average/AverageDiscountedReturn -45.9326 +MetaTest/Average/AverageReturn -45.9326 +MetaTest/Average/Iteration 366 +MetaTest/Average/MaxReturn -39.7649 +MetaTest/Average/MinReturn -55.9477 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.93733 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.9326 +MetaTest/__unnamed_task__/AverageReturn -45.9326 +MetaTest/__unnamed_task__/Iteration 366 +MetaTest/__unnamed_task__/MaxReturn -39.7649 +MetaTest/__unnamed_task__/MinReturn -55.9477 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.93733 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7616e+07 +__unnamed_task__/AverageDiscountedReturn -26.184 +__unnamed_task__/AverageReturn -47.2083 +__unnamed_task__/Iteration 366 +__unnamed_task__/MaxReturn -37.9778 +__unnamed_task__/MinReturn -59.8536 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.00732 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 02:48:54 | [maml_trainer] epoch #367 | Sampling for adapation and meta-testing... +2025-04-11 02:52:53 | [maml_trainer] epoch #367 | Finished meta-testing... +2025-04-11 02:52:53 | [maml_trainer] epoch #367 | Saving snapshot... +2025-04-11 02:53:15 | [maml_trainer] epoch #367 | Saved +2025-04-11 02:53:15 | [maml_trainer] epoch #367 | Time 641639.76 s +2025-04-11 02:53:15 | [maml_trainer] epoch #367 | EpochTime 1702.07 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.1677 +Average/AverageReturn -47.9124 +Average/Iteration 367 +Average/MaxReturn -39.5115 +Average/MinReturn -167.938 +Average/NumEpisodes 120 +Average/StdReturn 11.7015 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73657 +GaussianMLPPolicy/KLAfter 0.00113668 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.76715e-05 +GaussianMLPPolicy/LossBefore 2.38419e-10 +GaussianMLPPolicy/dLoss 3.76717e-05 +Iteration 367 +MetaTest/Average/AverageDiscountedReturn -47.2841 +MetaTest/Average/AverageReturn -47.2841 +MetaTest/Average/Iteration 367 +MetaTest/Average/MaxReturn -41.1249 +MetaTest/Average/MinReturn -59.7061 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.25877 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2841 +MetaTest/__unnamed_task__/AverageReturn -47.2841 +MetaTest/__unnamed_task__/Iteration 367 +MetaTest/__unnamed_task__/MaxReturn -41.1249 +MetaTest/__unnamed_task__/MinReturn -59.7061 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.25877 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7664e+07 +__unnamed_task__/AverageDiscountedReturn -26.1677 +__unnamed_task__/AverageReturn -47.9124 +__unnamed_task__/Iteration 367 +__unnamed_task__/MaxReturn -39.5115 +__unnamed_task__/MinReturn -167.938 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.7015 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 03:33:41 | [maml_trainer] epoch #368 | Sampling for adapation and meta-testing... +2025-04-11 03:40:32 | [maml_trainer] epoch #368 | Finished meta-testing... +2025-04-11 03:40:32 | [maml_trainer] epoch #368 | Saving snapshot... +2025-04-11 03:41:10 | [maml_trainer] epoch #368 | Saved +2025-04-11 03:41:10 | [maml_trainer] epoch #368 | Time 644514.19 s +2025-04-11 03:41:10 | [maml_trainer] epoch #368 | EpochTime 2874.42 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.7039 +Average/AverageReturn -49.3855 +Average/Iteration 368 +Average/MaxReturn -41.209 +Average/MinReturn -155.244 +Average/NumEpisodes 120 +Average/StdReturn 12.1678 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73682 +GaussianMLPPolicy/KLAfter 0.00189755 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.18623e-05 +GaussianMLPPolicy/LossBefore 1.94708e-09 +GaussianMLPPolicy/dLoss -3.18603e-05 +Iteration 368 +MetaTest/Average/AverageDiscountedReturn -50.1332 +MetaTest/Average/AverageReturn -50.1332 +MetaTest/Average/Iteration 368 +MetaTest/Average/MaxReturn -41.2118 +MetaTest/Average/MinReturn -120.479 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.6617 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1332 +MetaTest/__unnamed_task__/AverageReturn -50.1332 +MetaTest/__unnamed_task__/Iteration 368 +MetaTest/__unnamed_task__/MaxReturn -41.2118 +MetaTest/__unnamed_task__/MinReturn -120.479 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.6617 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7712e+07 +__unnamed_task__/AverageDiscountedReturn -26.7039 +__unnamed_task__/AverageReturn -49.3855 +__unnamed_task__/Iteration 368 +__unnamed_task__/MaxReturn -41.209 +__unnamed_task__/MinReturn -155.244 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.1678 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 04:21:52 | [maml_trainer] epoch #369 | Sampling for adapation and meta-testing... +2025-04-11 04:28:38 | [maml_trainer] epoch #369 | Finished meta-testing... +2025-04-11 04:28:38 | [maml_trainer] epoch #369 | Saving snapshot... +2025-04-11 04:29:18 | [maml_trainer] epoch #369 | Saved +2025-04-11 04:29:18 | [maml_trainer] epoch #369 | Time 647402.81 s +2025-04-11 04:29:18 | [maml_trainer] epoch #369 | EpochTime 2888.61 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.1171 +Average/AverageReturn -48.1624 +Average/Iteration 369 +Average/MaxReturn -40.1814 +Average/MinReturn -132.741 +Average/NumEpisodes 120 +Average/StdReturn 10.4467 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73655 +GaussianMLPPolicy/KLAfter 0.00171515 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.33855e-05 +GaussianMLPPolicy/LossBefore 1.54972e-09 +GaussianMLPPolicy/dLoss -2.33839e-05 +Iteration 369 +MetaTest/Average/AverageDiscountedReturn -46.1629 +MetaTest/Average/AverageReturn -46.1629 +MetaTest/Average/Iteration 369 +MetaTest/Average/MaxReturn -41.1265 +MetaTest/Average/MinReturn -54.1548 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.39795 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.1629 +MetaTest/__unnamed_task__/AverageReturn -46.1629 +MetaTest/__unnamed_task__/Iteration 369 +MetaTest/__unnamed_task__/MaxReturn -41.1265 +MetaTest/__unnamed_task__/MinReturn -54.1548 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.39795 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.776e+07 +__unnamed_task__/AverageDiscountedReturn -26.1171 +__unnamed_task__/AverageReturn -48.1624 +__unnamed_task__/Iteration 369 +__unnamed_task__/MaxReturn -40.1814 +__unnamed_task__/MinReturn -132.741 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.4467 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 05:05:56 | [maml_trainer] epoch #370 | Sampling for adapation and meta-testing... +2025-04-11 05:09:58 | [maml_trainer] epoch #370 | Finished meta-testing... +2025-04-11 05:09:58 | [maml_trainer] epoch #370 | Saving snapshot... +2025-04-11 05:10:19 | [maml_trainer] epoch #370 | Saved +2025-04-11 05:10:19 | [maml_trainer] epoch #370 | Time 649863.91 s +2025-04-11 05:10:19 | [maml_trainer] epoch #370 | EpochTime 2461.10 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.9126 +Average/AverageReturn -49.8282 +Average/Iteration 370 +Average/MaxReturn -40.2523 +Average/MinReturn -120.727 +Average/NumEpisodes 120 +Average/StdReturn 10.583 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73576 +GaussianMLPPolicy/KLAfter 0.00169278 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.47968e-05 +GaussianMLPPolicy/LossBefore 5.20547e-09 +GaussianMLPPolicy/dLoss -6.47916e-05 +Iteration 370 +MetaTest/Average/AverageDiscountedReturn -47.4627 +MetaTest/Average/AverageReturn -47.4627 +MetaTest/Average/Iteration 370 +MetaTest/Average/MaxReturn -40.4365 +MetaTest/Average/MinReturn -61.7782 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.63647 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4627 +MetaTest/__unnamed_task__/AverageReturn -47.4627 +MetaTest/__unnamed_task__/Iteration 370 +MetaTest/__unnamed_task__/MaxReturn -40.4365 +MetaTest/__unnamed_task__/MinReturn -61.7782 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.63647 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7808e+07 +__unnamed_task__/AverageDiscountedReturn -26.9126 +__unnamed_task__/AverageReturn -49.8282 +__unnamed_task__/Iteration 370 +__unnamed_task__/MaxReturn -40.2523 +__unnamed_task__/MinReturn -120.727 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.583 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 05:34:22 | [maml_trainer] epoch #371 | Sampling for adapation and meta-testing... +2025-04-11 05:38:22 | [maml_trainer] epoch #371 | Finished meta-testing... +2025-04-11 05:38:22 | [maml_trainer] epoch #371 | Saving snapshot... +2025-04-11 05:38:42 | [maml_trainer] epoch #371 | Saved +2025-04-11 05:38:42 | [maml_trainer] epoch #371 | Time 651566.83 s +2025-04-11 05:38:42 | [maml_trainer] epoch #371 | EpochTime 1702.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.6905 +Average/AverageReturn -50.4786 +Average/Iteration 371 +Average/MaxReturn -39.4588 +Average/MinReturn -161.65 +Average/NumEpisodes 120 +Average/StdReturn 17.1082 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73489 +GaussianMLPPolicy/KLAfter 0.00138772 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.95871e-05 +GaussianMLPPolicy/LossBefore -7.53005e-09 +GaussianMLPPolicy/dLoss -4.95946e-05 +Iteration 371 +MetaTest/Average/AverageDiscountedReturn -50.0365 +MetaTest/Average/AverageReturn -50.0365 +MetaTest/Average/Iteration 371 +MetaTest/Average/MaxReturn -42.4177 +MetaTest/Average/MinReturn -62.7385 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.98528 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0365 +MetaTest/__unnamed_task__/AverageReturn -50.0365 +MetaTest/__unnamed_task__/Iteration 371 +MetaTest/__unnamed_task__/MaxReturn -42.4177 +MetaTest/__unnamed_task__/MinReturn -62.7385 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.98528 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7856e+07 +__unnamed_task__/AverageDiscountedReturn -26.6905 +__unnamed_task__/AverageReturn -50.4786 +__unnamed_task__/Iteration 371 +__unnamed_task__/MaxReturn -39.4588 +__unnamed_task__/MinReturn -161.65 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 17.1082 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 06:02:39 | [maml_trainer] epoch #372 | Sampling for adapation and meta-testing... +2025-04-11 06:06:38 | [maml_trainer] epoch #372 | Finished meta-testing... +2025-04-11 06:06:38 | [maml_trainer] epoch #372 | Saving snapshot... +2025-04-11 06:06:59 | [maml_trainer] epoch #372 | Saved +2025-04-11 06:06:59 | [maml_trainer] epoch #372 | Time 653263.08 s +2025-04-11 06:06:59 | [maml_trainer] epoch #372 | EpochTime 1696.25 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.0621 +Average/AverageReturn -52.1296 +Average/Iteration 372 +Average/MaxReturn -39.4332 +Average/MinReturn -172.221 +Average/NumEpisodes 120 +Average/StdReturn 21.1537 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73417 +GaussianMLPPolicy/KLAfter 0.000972363 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.61174e-05 +GaussianMLPPolicy/LossBefore 2.08616e-09 +GaussianMLPPolicy/dLoss 6.61195e-05 +Iteration 372 +MetaTest/Average/AverageDiscountedReturn -46.7254 +MetaTest/Average/AverageReturn -46.7254 +MetaTest/Average/Iteration 372 +MetaTest/Average/MaxReturn -42.8627 +MetaTest/Average/MinReturn -52.7199 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.34193 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.7254 +MetaTest/__unnamed_task__/AverageReturn -46.7254 +MetaTest/__unnamed_task__/Iteration 372 +MetaTest/__unnamed_task__/MaxReturn -42.8627 +MetaTest/__unnamed_task__/MinReturn -52.7199 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.34193 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7904e+07 +__unnamed_task__/AverageDiscountedReturn -27.0621 +__unnamed_task__/AverageReturn -52.1296 +__unnamed_task__/Iteration 372 +__unnamed_task__/MaxReturn -39.4332 +__unnamed_task__/MinReturn -172.221 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 21.1537 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 06:31:03 | [maml_trainer] epoch #373 | Sampling for adapation and meta-testing... +2025-04-11 06:35:06 | [maml_trainer] epoch #373 | Finished meta-testing... +2025-04-11 06:35:06 | [maml_trainer] epoch #373 | Saving snapshot... +2025-04-11 06:35:28 | [maml_trainer] epoch #373 | Saved +2025-04-11 06:35:28 | [maml_trainer] epoch #373 | Time 654972.85 s +2025-04-11 06:35:28 | [maml_trainer] epoch #373 | EpochTime 1709.76 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.4998 +Average/AverageReturn -48.8809 +Average/Iteration 373 +Average/MaxReturn -41.3087 +Average/MinReturn -161.216 +Average/NumEpisodes 120 +Average/StdReturn 12.3185 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73447 +GaussianMLPPolicy/KLAfter 0.000608993 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.01188e-05 +GaussianMLPPolicy/LossBefore -4.41074e-09 +GaussianMLPPolicy/dLoss 2.01144e-05 +Iteration 373 +MetaTest/Average/AverageDiscountedReturn -47.1347 +MetaTest/Average/AverageReturn -47.1347 +MetaTest/Average/Iteration 373 +MetaTest/Average/MaxReturn -40.6042 +MetaTest/Average/MinReturn -67.7003 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.40341 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.1347 +MetaTest/__unnamed_task__/AverageReturn -47.1347 +MetaTest/__unnamed_task__/Iteration 373 +MetaTest/__unnamed_task__/MaxReturn -40.6042 +MetaTest/__unnamed_task__/MinReturn -67.7003 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.40341 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.7952e+07 +__unnamed_task__/AverageDiscountedReturn -26.4998 +__unnamed_task__/AverageReturn -48.8809 +__unnamed_task__/Iteration 373 +__unnamed_task__/MaxReturn -41.3087 +__unnamed_task__/MinReturn -161.216 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.3185 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 06:59:32 | [maml_trainer] epoch #374 | Sampling for adapation and meta-testing... +2025-04-11 07:03:36 | [maml_trainer] epoch #374 | Finished meta-testing... +2025-04-11 07:03:36 | [maml_trainer] epoch #374 | Saving snapshot... +2025-04-11 07:03:58 | [maml_trainer] epoch #374 | Saved +2025-04-11 07:03:58 | [maml_trainer] epoch #374 | Time 656682.43 s +2025-04-11 07:03:58 | [maml_trainer] epoch #374 | EpochTime 1709.57 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.1725 +Average/AverageReturn -47.4718 +Average/Iteration 374 +Average/MaxReturn -39.4356 +Average/MinReturn -66.3626 +Average/NumEpisodes 120 +Average/StdReturn 4.67411 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73413 +GaussianMLPPolicy/KLAfter 0.00095764 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.59007e-06 +GaussianMLPPolicy/LossBefore -1.16825e-08 +GaussianMLPPolicy/dLoss 9.57839e-06 +Iteration 374 +MetaTest/Average/AverageDiscountedReturn -47.468 +MetaTest/Average/AverageReturn -47.468 +MetaTest/Average/Iteration 374 +MetaTest/Average/MaxReturn -41.5041 +MetaTest/Average/MinReturn -54.749 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.93201 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.468 +MetaTest/__unnamed_task__/AverageReturn -47.468 +MetaTest/__unnamed_task__/Iteration 374 +MetaTest/__unnamed_task__/MaxReturn -41.5041 +MetaTest/__unnamed_task__/MinReturn -54.749 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.93201 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8e+07 +__unnamed_task__/AverageDiscountedReturn -26.1725 +__unnamed_task__/AverageReturn -47.4718 +__unnamed_task__/Iteration 374 +__unnamed_task__/MaxReturn -39.4356 +__unnamed_task__/MinReturn -66.3626 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.67411 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 07:28:10 | [maml_trainer] epoch #375 | Sampling for adapation and meta-testing... +2025-04-11 07:32:17 | [maml_trainer] epoch #375 | Finished meta-testing... +2025-04-11 07:32:17 | [maml_trainer] epoch #375 | Saving snapshot... +2025-04-11 07:32:39 | [maml_trainer] epoch #375 | Saved +2025-04-11 07:32:39 | [maml_trainer] epoch #375 | Time 658403.43 s +2025-04-11 07:32:39 | [maml_trainer] epoch #375 | EpochTime 1720.99 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8014 +Average/AverageReturn -50.4797 +Average/Iteration 375 +Average/MaxReturn -38.409 +Average/MinReturn -170.945 +Average/NumEpisodes 120 +Average/StdReturn 18.0741 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73394 +GaussianMLPPolicy/KLAfter 0.00132386 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.65925e-05 +GaussianMLPPolicy/LossBefore -5.126e-09 +GaussianMLPPolicy/dLoss -2.65976e-05 +Iteration 375 +MetaTest/Average/AverageDiscountedReturn -53.6164 +MetaTest/Average/AverageReturn -53.6164 +MetaTest/Average/Iteration 375 +MetaTest/Average/MaxReturn -40.3096 +MetaTest/Average/MinReturn -157.219 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 24.1471 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.6164 +MetaTest/__unnamed_task__/AverageReturn -53.6164 +MetaTest/__unnamed_task__/Iteration 375 +MetaTest/__unnamed_task__/MaxReturn -40.3096 +MetaTest/__unnamed_task__/MinReturn -157.219 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 24.1471 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8048e+07 +__unnamed_task__/AverageDiscountedReturn -26.8014 +__unnamed_task__/AverageReturn -50.4797 +__unnamed_task__/Iteration 375 +__unnamed_task__/MaxReturn -38.409 +__unnamed_task__/MinReturn -170.945 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 18.0741 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 07:56:46 | [maml_trainer] epoch #376 | Sampling for adapation and meta-testing... +2025-04-11 08:00:48 | [maml_trainer] epoch #376 | Finished meta-testing... +2025-04-11 08:00:48 | [maml_trainer] epoch #376 | Saving snapshot... +2025-04-11 08:01:10 | [maml_trainer] epoch #376 | Saved +2025-04-11 08:01:10 | [maml_trainer] epoch #376 | Time 660114.04 s +2025-04-11 08:01:10 | [maml_trainer] epoch #376 | EpochTime 1710.61 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8789 +Average/AverageReturn -50.3198 +Average/Iteration 376 +Average/MaxReturn -38.997 +Average/MinReturn -163.955 +Average/NumEpisodes 120 +Average/StdReturn 14.5844 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7343 +GaussianMLPPolicy/KLAfter 0.00318839 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000132923 +GaussianMLPPolicy/LossBefore 5.28494e-09 +GaussianMLPPolicy/dLoss 0.000132928 +Iteration 376 +MetaTest/Average/AverageDiscountedReturn -53.598 +MetaTest/Average/AverageReturn -53.598 +MetaTest/Average/Iteration 376 +MetaTest/Average/MaxReturn -42.5656 +MetaTest/Average/MinReturn -171.105 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 27.4439 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.598 +MetaTest/__unnamed_task__/AverageReturn -53.598 +MetaTest/__unnamed_task__/Iteration 376 +MetaTest/__unnamed_task__/MaxReturn -42.5656 +MetaTest/__unnamed_task__/MinReturn -171.105 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 27.4439 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8096e+07 +__unnamed_task__/AverageDiscountedReturn -26.8789 +__unnamed_task__/AverageReturn -50.3198 +__unnamed_task__/Iteration 376 +__unnamed_task__/MaxReturn -38.997 +__unnamed_task__/MinReturn -163.955 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.5844 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 08:25:29 | [maml_trainer] epoch #377 | Sampling for adapation and meta-testing... +2025-04-11 08:29:33 | [maml_trainer] epoch #377 | Finished meta-testing... +2025-04-11 08:29:33 | [maml_trainer] epoch #377 | Saving snapshot... +2025-04-11 08:29:55 | [maml_trainer] epoch #377 | Saved +2025-04-11 08:29:55 | [maml_trainer] epoch #377 | Time 661839.15 s +2025-04-11 08:29:55 | [maml_trainer] epoch #377 | EpochTime 1725.11 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.7426 +Average/AverageReturn -51.7024 +Average/Iteration 377 +Average/MaxReturn -39.5282 +Average/MinReturn -166.797 +Average/NumEpisodes 120 +Average/StdReturn 21.1892 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73508 +GaussianMLPPolicy/KLAfter 0.00419984 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.55652e-05 +GaussianMLPPolicy/LossBefore 5.96047e-10 +GaussianMLPPolicy/dLoss 2.55658e-05 +Iteration 377 +MetaTest/Average/AverageDiscountedReturn -50.0513 +MetaTest/Average/AverageReturn -50.0513 +MetaTest/Average/Iteration 377 +MetaTest/Average/MaxReturn -40.5824 +MetaTest/Average/MinReturn -69.0231 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.66534 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.0513 +MetaTest/__unnamed_task__/AverageReturn -50.0513 +MetaTest/__unnamed_task__/Iteration 377 +MetaTest/__unnamed_task__/MaxReturn -40.5824 +MetaTest/__unnamed_task__/MinReturn -69.0231 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.66534 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8144e+07 +__unnamed_task__/AverageDiscountedReturn -26.7426 +__unnamed_task__/AverageReturn -51.7024 +__unnamed_task__/Iteration 377 +__unnamed_task__/MaxReturn -39.5282 +__unnamed_task__/MinReturn -166.797 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 21.1892 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 08:54:19 | [maml_trainer] epoch #378 | Sampling for adapation and meta-testing... +2025-04-11 08:58:21 | [maml_trainer] epoch #378 | Finished meta-testing... +2025-04-11 08:58:21 | [maml_trainer] epoch #378 | Saving snapshot... +2025-04-11 08:58:43 | [maml_trainer] epoch #378 | Saved +2025-04-11 08:58:43 | [maml_trainer] epoch #378 | Time 663566.99 s +2025-04-11 08:58:43 | [maml_trainer] epoch #378 | EpochTime 1727.83 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.6177 +Average/AverageReturn -50.0353 +Average/Iteration 378 +Average/MaxReturn -39.1544 +Average/MinReturn -144.656 +Average/NumEpisodes 120 +Average/StdReturn 13.3339 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73587 +GaussianMLPPolicy/KLAfter 0.00408746 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.05992e-05 +GaussianMLPPolicy/LossBefore -1.38283e-08 +GaussianMLPPolicy/dLoss 2.05854e-05 +Iteration 378 +MetaTest/Average/AverageDiscountedReturn -52.1532 +MetaTest/Average/AverageReturn -52.1532 +MetaTest/Average/Iteration 378 +MetaTest/Average/MaxReturn -40.3568 +MetaTest/Average/MinReturn -111.777 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.69 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1532 +MetaTest/__unnamed_task__/AverageReturn -52.1532 +MetaTest/__unnamed_task__/Iteration 378 +MetaTest/__unnamed_task__/MaxReturn -40.3568 +MetaTest/__unnamed_task__/MinReturn -111.777 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.69 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8192e+07 +__unnamed_task__/AverageDiscountedReturn -26.6177 +__unnamed_task__/AverageReturn -50.0353 +__unnamed_task__/Iteration 378 +__unnamed_task__/MaxReturn -39.1544 +__unnamed_task__/MinReturn -144.656 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.3339 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 09:22:47 | [maml_trainer] epoch #379 | Sampling for adapation and meta-testing... +2025-04-11 09:26:47 | [maml_trainer] epoch #379 | Finished meta-testing... +2025-04-11 09:26:47 | [maml_trainer] epoch #379 | Saving snapshot... +2025-04-11 09:27:09 | [maml_trainer] epoch #379 | Saved +2025-04-11 09:27:09 | [maml_trainer] epoch #379 | Time 665273.55 s +2025-04-11 09:27:09 | [maml_trainer] epoch #379 | EpochTime 1706.56 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.4689 +Average/AverageReturn -49.4823 +Average/Iteration 379 +Average/MaxReturn -39.5882 +Average/MinReturn -174.397 +Average/NumEpisodes 120 +Average/StdReturn 14.2985 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73614 +GaussianMLPPolicy/KLAfter 0.00233615 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.02268e-05 +GaussianMLPPolicy/LossBefore -4.45048e-09 +GaussianMLPPolicy/dLoss -3.02312e-05 +Iteration 379 +MetaTest/Average/AverageDiscountedReturn -48.1556 +MetaTest/Average/AverageReturn -48.1556 +MetaTest/Average/Iteration 379 +MetaTest/Average/MaxReturn -42.6227 +MetaTest/Average/MinReturn -56.4624 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.74185 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1556 +MetaTest/__unnamed_task__/AverageReturn -48.1556 +MetaTest/__unnamed_task__/Iteration 379 +MetaTest/__unnamed_task__/MaxReturn -42.6227 +MetaTest/__unnamed_task__/MinReturn -56.4624 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.74185 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.824e+07 +__unnamed_task__/AverageDiscountedReturn -26.4689 +__unnamed_task__/AverageReturn -49.4823 +__unnamed_task__/Iteration 379 +__unnamed_task__/MaxReturn -39.5882 +__unnamed_task__/MinReturn -174.397 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.2985 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 09:51:15 | [maml_trainer] epoch #380 | Sampling for adapation and meta-testing... +2025-04-11 09:55:17 | [maml_trainer] epoch #380 | Finished meta-testing... +2025-04-11 09:55:17 | [maml_trainer] epoch #380 | Saving snapshot... +2025-04-11 09:55:39 | [maml_trainer] epoch #380 | Saved +2025-04-11 09:55:39 | [maml_trainer] epoch #380 | Time 666983.20 s +2025-04-11 09:55:39 | [maml_trainer] epoch #380 | EpochTime 1709.65 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.1483 +Average/AverageReturn -49.027 +Average/Iteration 380 +Average/MaxReturn -37.7841 +Average/MinReturn -176.647 +Average/NumEpisodes 120 +Average/StdReturn 15.1789 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7368 +GaussianMLPPolicy/KLAfter 0.00110606 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.30037e-06 +GaussianMLPPolicy/LossBefore -2.82129e-09 +GaussianMLPPolicy/dLoss 3.29755e-06 +Iteration 380 +MetaTest/Average/AverageDiscountedReturn -47.932 +MetaTest/Average/AverageReturn -47.932 +MetaTest/Average/Iteration 380 +MetaTest/Average/MaxReturn -43.4315 +MetaTest/Average/MinReturn -52.3472 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.76516 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.932 +MetaTest/__unnamed_task__/AverageReturn -47.932 +MetaTest/__unnamed_task__/Iteration 380 +MetaTest/__unnamed_task__/MaxReturn -43.4315 +MetaTest/__unnamed_task__/MinReturn -52.3472 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.76516 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8288e+07 +__unnamed_task__/AverageDiscountedReturn -26.1483 +__unnamed_task__/AverageReturn -49.027 +__unnamed_task__/Iteration 380 +__unnamed_task__/MaxReturn -37.7841 +__unnamed_task__/MinReturn -176.647 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.1789 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 10:19:54 | [maml_trainer] epoch #381 | Sampling for adapation and meta-testing... +2025-04-11 10:24:02 | [maml_trainer] epoch #381 | Finished meta-testing... +2025-04-11 10:24:02 | [maml_trainer] epoch #381 | Saving snapshot... +2025-04-11 10:24:25 | [maml_trainer] epoch #381 | Saved +2025-04-11 10:24:25 | [maml_trainer] epoch #381 | Time 668709.11 s +2025-04-11 10:24:25 | [maml_trainer] epoch #381 | EpochTime 1725.91 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.0862 +Average/AverageReturn -48.5195 +Average/Iteration 381 +Average/MaxReturn -38.9155 +Average/MinReturn -171.287 +Average/NumEpisodes 120 +Average/StdReturn 12.2734 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73679 +GaussianMLPPolicy/KLAfter 0.00321483 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.45343e-05 +GaussianMLPPolicy/LossBefore -1.24971e-08 +GaussianMLPPolicy/dLoss -2.45468e-05 +Iteration 381 +MetaTest/Average/AverageDiscountedReturn -52.2272 +MetaTest/Average/AverageReturn -52.2272 +MetaTest/Average/Iteration 381 +MetaTest/Average/MaxReturn -42.265 +MetaTest/Average/MinReturn -134.087 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 19.0861 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.2272 +MetaTest/__unnamed_task__/AverageReturn -52.2272 +MetaTest/__unnamed_task__/Iteration 381 +MetaTest/__unnamed_task__/MaxReturn -42.265 +MetaTest/__unnamed_task__/MinReturn -134.087 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 19.0861 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8336e+07 +__unnamed_task__/AverageDiscountedReturn -26.0862 +__unnamed_task__/AverageReturn -48.5195 +__unnamed_task__/Iteration 381 +__unnamed_task__/MaxReturn -38.9155 +__unnamed_task__/MinReturn -171.287 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.2734 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 10:48:57 | [maml_trainer] epoch #382 | Sampling for adapation and meta-testing... +2025-04-11 10:53:01 | [maml_trainer] epoch #382 | Finished meta-testing... +2025-04-11 10:53:01 | [maml_trainer] epoch #382 | Saving snapshot... +2025-04-11 10:53:23 | [maml_trainer] epoch #382 | Saved +2025-04-11 10:53:23 | [maml_trainer] epoch #382 | Time 670447.48 s +2025-04-11 10:53:23 | [maml_trainer] epoch #382 | EpochTime 1738.36 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.5091 +Average/AverageReturn -49.4704 +Average/Iteration 382 +Average/MaxReturn -40.7067 +Average/MinReturn -113.737 +Average/NumEpisodes 120 +Average/StdReturn 9.34912 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73679 +GaussianMLPPolicy/KLAfter 0.00238727 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 4.21964e-05 +GaussianMLPPolicy/LossBefore -5.24521e-09 +GaussianMLPPolicy/dLoss -4.22016e-05 +Iteration 382 +MetaTest/Average/AverageDiscountedReturn -50.4525 +MetaTest/Average/AverageReturn -50.4525 +MetaTest/Average/Iteration 382 +MetaTest/Average/MaxReturn -42.0124 +MetaTest/Average/MinReturn -91.2023 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.79487 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4525 +MetaTest/__unnamed_task__/AverageReturn -50.4525 +MetaTest/__unnamed_task__/Iteration 382 +MetaTest/__unnamed_task__/MaxReturn -42.0124 +MetaTest/__unnamed_task__/MinReturn -91.2023 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.79487 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8384e+07 +__unnamed_task__/AverageDiscountedReturn -26.5091 +__unnamed_task__/AverageReturn -49.4704 +__unnamed_task__/Iteration 382 +__unnamed_task__/MaxReturn -40.7067 +__unnamed_task__/MinReturn -113.737 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.34912 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 11:17:43 | [maml_trainer] epoch #383 | Sampling for adapation and meta-testing... +2025-04-11 11:21:45 | [maml_trainer] epoch #383 | Finished meta-testing... +2025-04-11 11:21:45 | [maml_trainer] epoch #383 | Saving snapshot... +2025-04-11 11:22:07 | [maml_trainer] epoch #383 | Saved +2025-04-11 11:22:07 | [maml_trainer] epoch #383 | Time 672171.40 s +2025-04-11 11:22:07 | [maml_trainer] epoch #383 | EpochTime 1723.92 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.5471 +Average/AverageReturn -50.2329 +Average/Iteration 383 +Average/MaxReturn -40.7223 +Average/MinReturn -151.881 +Average/NumEpisodes 120 +Average/StdReturn 12.9272 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73586 +GaussianMLPPolicy/KLAfter 0.00236083 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.86939e-05 +GaussianMLPPolicy/LossBefore -6.55651e-09 +GaussianMLPPolicy/dLoss 4.86873e-05 +Iteration 383 +MetaTest/Average/AverageDiscountedReturn -50.9639 +MetaTest/Average/AverageReturn -50.9639 +MetaTest/Average/Iteration 383 +MetaTest/Average/MaxReturn -44.8632 +MetaTest/Average/MinReturn -72.0132 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.70137 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9639 +MetaTest/__unnamed_task__/AverageReturn -50.9639 +MetaTest/__unnamed_task__/Iteration 383 +MetaTest/__unnamed_task__/MaxReturn -44.8632 +MetaTest/__unnamed_task__/MinReturn -72.0132 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.70137 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8432e+07 +__unnamed_task__/AverageDiscountedReturn -26.5471 +__unnamed_task__/AverageReturn -50.2329 +__unnamed_task__/Iteration 383 +__unnamed_task__/MaxReturn -40.7223 +__unnamed_task__/MinReturn -151.881 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.9272 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 11:46:27 | [maml_trainer] epoch #384 | Sampling for adapation and meta-testing... +2025-04-11 11:50:27 | [maml_trainer] epoch #384 | Finished meta-testing... +2025-04-11 11:50:27 | [maml_trainer] epoch #384 | Saving snapshot... +2025-04-11 11:50:48 | [maml_trainer] epoch #384 | Saved +2025-04-11 11:50:48 | [maml_trainer] epoch #384 | Time 673892.84 s +2025-04-11 11:50:48 | [maml_trainer] epoch #384 | EpochTime 1721.44 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8089 +Average/AverageReturn -50.2248 +Average/Iteration 384 +Average/MaxReturn -40.5573 +Average/MinReturn -104.318 +Average/NumEpisodes 120 +Average/StdReturn 7.09011 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73462 +GaussianMLPPolicy/KLAfter 0.00172223 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.84991e-05 +GaussianMLPPolicy/LossBefore 4.29153e-09 +GaussianMLPPolicy/dLoss -2.84948e-05 +Iteration 384 +MetaTest/Average/AverageDiscountedReturn -50.324 +MetaTest/Average/AverageReturn -50.324 +MetaTest/Average/Iteration 384 +MetaTest/Average/MaxReturn -41.4688 +MetaTest/Average/MinReturn -68.7757 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.99252 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.324 +MetaTest/__unnamed_task__/AverageReturn -50.324 +MetaTest/__unnamed_task__/Iteration 384 +MetaTest/__unnamed_task__/MaxReturn -41.4688 +MetaTest/__unnamed_task__/MinReturn -68.7757 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.99252 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.848e+07 +__unnamed_task__/AverageDiscountedReturn -26.8089 +__unnamed_task__/AverageReturn -50.2248 +__unnamed_task__/Iteration 384 +__unnamed_task__/MaxReturn -40.5573 +__unnamed_task__/MinReturn -104.318 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.09011 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 12:15:06 | [maml_trainer] epoch #385 | Sampling for adapation and meta-testing... +2025-04-11 12:19:08 | [maml_trainer] epoch #385 | Finished meta-testing... +2025-04-11 12:19:08 | [maml_trainer] epoch #385 | Saving snapshot... +2025-04-11 12:19:30 | [maml_trainer] epoch #385 | Saved +2025-04-11 12:19:30 | [maml_trainer] epoch #385 | Time 675614.67 s +2025-04-11 12:19:30 | [maml_trainer] epoch #385 | EpochTime 1721.83 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.8814 +Average/AverageReturn -50.9412 +Average/Iteration 385 +Average/MaxReturn -41.4396 +Average/MinReturn -123.622 +Average/NumEpisodes 120 +Average/StdReturn 10.09 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73322 +GaussianMLPPolicy/KLAfter 0.00201219 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.02756e-05 +GaussianMLPPolicy/LossBefore -3.45707e-09 +GaussianMLPPolicy/dLoss -2.02791e-05 +Iteration 385 +MetaTest/Average/AverageDiscountedReturn -49.2546 +MetaTest/Average/AverageReturn -49.2546 +MetaTest/Average/Iteration 385 +MetaTest/Average/MaxReturn -42.4525 +MetaTest/Average/MinReturn -66.1154 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.48041 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2546 +MetaTest/__unnamed_task__/AverageReturn -49.2546 +MetaTest/__unnamed_task__/Iteration 385 +MetaTest/__unnamed_task__/MaxReturn -42.4525 +MetaTest/__unnamed_task__/MinReturn -66.1154 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.48041 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8528e+07 +__unnamed_task__/AverageDiscountedReturn -26.8814 +__unnamed_task__/AverageReturn -50.9412 +__unnamed_task__/Iteration 385 +__unnamed_task__/MaxReturn -41.4396 +__unnamed_task__/MinReturn -123.622 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.09 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 12:43:49 | [maml_trainer] epoch #386 | Sampling for adapation and meta-testing... +2025-04-11 12:47:53 | [maml_trainer] epoch #386 | Finished meta-testing... +2025-04-11 12:47:53 | [maml_trainer] epoch #386 | Saving snapshot... +2025-04-11 12:48:14 | [maml_trainer] epoch #386 | Saved +2025-04-11 12:48:14 | [maml_trainer] epoch #386 | Time 677338.53 s +2025-04-11 12:48:14 | [maml_trainer] epoch #386 | EpochTime 1723.85 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.6725 +Average/AverageReturn -50.1921 +Average/Iteration 386 +Average/MaxReturn -42.6725 +Average/MinReturn -89.5317 +Average/NumEpisodes 120 +Average/StdReturn 5.62343 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.7327 +GaussianMLPPolicy/KLAfter 0.00183638 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000140135 +GaussianMLPPolicy/LossBefore 1.15236e-09 +GaussianMLPPolicy/dLoss 0.000140136 +Iteration 386 +MetaTest/Average/AverageDiscountedReturn -50.5005 +MetaTest/Average/AverageReturn -50.5005 +MetaTest/Average/Iteration 386 +MetaTest/Average/MaxReturn -43.324 +MetaTest/Average/MinReturn -60.3857 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.38695 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5005 +MetaTest/__unnamed_task__/AverageReturn -50.5005 +MetaTest/__unnamed_task__/Iteration 386 +MetaTest/__unnamed_task__/MaxReturn -43.324 +MetaTest/__unnamed_task__/MinReturn -60.3857 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.38695 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8576e+07 +__unnamed_task__/AverageDiscountedReturn -26.6725 +__unnamed_task__/AverageReturn -50.1921 +__unnamed_task__/Iteration 386 +__unnamed_task__/MaxReturn -42.6725 +__unnamed_task__/MinReturn -89.5317 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.62343 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 13:12:43 | [maml_trainer] epoch #387 | Sampling for adapation and meta-testing... +2025-04-11 13:16:48 | [maml_trainer] epoch #387 | Finished meta-testing... +2025-04-11 13:16:48 | [maml_trainer] epoch #387 | Saving snapshot... +2025-04-11 13:17:09 | [maml_trainer] epoch #387 | Saved +2025-04-11 13:17:09 | [maml_trainer] epoch #387 | Time 679073.78 s +2025-04-11 13:17:09 | [maml_trainer] epoch #387 | EpochTime 1735.25 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.9034 +Average/AverageReturn -51.1056 +Average/Iteration 387 +Average/MaxReturn -41.3693 +Average/MinReturn -167.581 +Average/NumEpisodes 120 +Average/StdReturn 11.4795 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73298 +GaussianMLPPolicy/KLAfter 0.00287621 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.83703e-05 +GaussianMLPPolicy/LossBefore 3.29812e-09 +GaussianMLPPolicy/dLoss -1.8367e-05 +Iteration 387 +MetaTest/Average/AverageDiscountedReturn -49.5632 +MetaTest/Average/AverageReturn -49.5632 +MetaTest/Average/Iteration 387 +MetaTest/Average/MaxReturn -43.1023 +MetaTest/Average/MinReturn -62.8795 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.84837 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5632 +MetaTest/__unnamed_task__/AverageReturn -49.5632 +MetaTest/__unnamed_task__/Iteration 387 +MetaTest/__unnamed_task__/MaxReturn -43.1023 +MetaTest/__unnamed_task__/MinReturn -62.8795 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.84837 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8624e+07 +__unnamed_task__/AverageDiscountedReturn -26.9034 +__unnamed_task__/AverageReturn -51.1056 +__unnamed_task__/Iteration 387 +__unnamed_task__/MaxReturn -41.3693 +__unnamed_task__/MinReturn -167.581 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.4795 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 13:41:32 | [maml_trainer] epoch #388 | Sampling for adapation and meta-testing... +2025-04-11 13:45:36 | [maml_trainer] epoch #388 | Finished meta-testing... +2025-04-11 13:45:36 | [maml_trainer] epoch #388 | Saving snapshot... +2025-04-11 13:45:59 | [maml_trainer] epoch #388 | Saved +2025-04-11 13:45:59 | [maml_trainer] epoch #388 | Time 680803.26 s +2025-04-11 13:45:59 | [maml_trainer] epoch #388 | EpochTime 1729.47 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.0426 +Average/AverageReturn -51.3022 +Average/Iteration 388 +Average/MaxReturn -42.0905 +Average/MinReturn -123.827 +Average/NumEpisodes 120 +Average/StdReturn 7.98074 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73373 +GaussianMLPPolicy/KLAfter 0.00399253 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.10963e-05 +GaussianMLPPolicy/LossBefore 1.77224e-08 +GaussianMLPPolicy/dLoss -7.10785e-05 +Iteration 388 +MetaTest/Average/AverageDiscountedReturn -49.1071 +MetaTest/Average/AverageReturn -49.1071 +MetaTest/Average/Iteration 388 +MetaTest/Average/MaxReturn -43.4157 +MetaTest/Average/MinReturn -53.5843 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.94185 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1071 +MetaTest/__unnamed_task__/AverageReturn -49.1071 +MetaTest/__unnamed_task__/Iteration 388 +MetaTest/__unnamed_task__/MaxReturn -43.4157 +MetaTest/__unnamed_task__/MinReturn -53.5843 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.94185 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8672e+07 +__unnamed_task__/AverageDiscountedReturn -27.0426 +__unnamed_task__/AverageReturn -51.3022 +__unnamed_task__/Iteration 388 +__unnamed_task__/MaxReturn -42.0905 +__unnamed_task__/MinReturn -123.827 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.98074 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 14:10:21 | [maml_trainer] epoch #389 | Sampling for adapation and meta-testing... +2025-04-11 14:14:25 | [maml_trainer] epoch #389 | Finished meta-testing... +2025-04-11 14:14:25 | [maml_trainer] epoch #389 | Saving snapshot... +2025-04-11 14:14:47 | [maml_trainer] epoch #389 | Saved +2025-04-11 14:14:47 | [maml_trainer] epoch #389 | Time 682531.22 s +2025-04-11 14:14:47 | [maml_trainer] epoch #389 | EpochTime 1727.96 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.4838 +Average/AverageReturn -52.7533 +Average/Iteration 389 +Average/MaxReturn -43.0586 +Average/MinReturn -104.702 +Average/NumEpisodes 120 +Average/StdReturn 8.56 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73309 +GaussianMLPPolicy/KLAfter 0.00300918 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000120506 +GaussianMLPPolicy/LossBefore -1.69277e-08 +GaussianMLPPolicy/dLoss -0.000120523 +Iteration 389 +MetaTest/Average/AverageDiscountedReturn -50.8135 +MetaTest/Average/AverageReturn -50.8135 +MetaTest/Average/Iteration 389 +MetaTest/Average/MaxReturn -43.8006 +MetaTest/Average/MinReturn -66.6299 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.19209 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.8135 +MetaTest/__unnamed_task__/AverageReturn -50.8135 +MetaTest/__unnamed_task__/Iteration 389 +MetaTest/__unnamed_task__/MaxReturn -43.8006 +MetaTest/__unnamed_task__/MinReturn -66.6299 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.19209 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.872e+07 +__unnamed_task__/AverageDiscountedReturn -27.4838 +__unnamed_task__/AverageReturn -52.7533 +__unnamed_task__/Iteration 389 +__unnamed_task__/MaxReturn -43.0586 +__unnamed_task__/MinReturn -104.702 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.56 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 14:39:01 | [maml_trainer] epoch #390 | Sampling for adapation and meta-testing... +2025-04-11 14:43:03 | [maml_trainer] epoch #390 | Finished meta-testing... +2025-04-11 14:43:03 | [maml_trainer] epoch #390 | Saving snapshot... +2025-04-11 14:43:25 | [maml_trainer] epoch #390 | Saved +2025-04-11 14:43:25 | [maml_trainer] epoch #390 | Time 684249.81 s +2025-04-11 14:43:25 | [maml_trainer] epoch #390 | EpochTime 1718.58 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2631 +Average/AverageReturn -52.2104 +Average/Iteration 390 +Average/MaxReturn -41.8582 +Average/MinReturn -103.319 +Average/NumEpisodes 120 +Average/StdReturn 7.16505 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73351 +GaussianMLPPolicy/KLAfter 0.00474778 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.49826e-05 +GaussianMLPPolicy/LossBefore -5.48363e-09 +GaussianMLPPolicy/dLoss -3.49881e-05 +Iteration 390 +MetaTest/Average/AverageDiscountedReturn -50.4766 +MetaTest/Average/AverageReturn -50.4766 +MetaTest/Average/Iteration 390 +MetaTest/Average/MaxReturn -44.0111 +MetaTest/Average/MinReturn -64.3624 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.3713 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4766 +MetaTest/__unnamed_task__/AverageReturn -50.4766 +MetaTest/__unnamed_task__/Iteration 390 +MetaTest/__unnamed_task__/MaxReturn -44.0111 +MetaTest/__unnamed_task__/MinReturn -64.3624 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.3713 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8768e+07 +__unnamed_task__/AverageDiscountedReturn -27.2631 +__unnamed_task__/AverageReturn -52.2104 +__unnamed_task__/Iteration 390 +__unnamed_task__/MaxReturn -41.8582 +__unnamed_task__/MinReturn -103.319 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.16505 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 15:07:49 | [maml_trainer] epoch #391 | Sampling for adapation and meta-testing... +2025-04-11 15:11:51 | [maml_trainer] epoch #391 | Finished meta-testing... +2025-04-11 15:11:51 | [maml_trainer] epoch #391 | Saving snapshot... +2025-04-11 15:12:12 | [maml_trainer] epoch #391 | Saved +2025-04-11 15:12:12 | [maml_trainer] epoch #391 | Time 685976.11 s +2025-04-11 15:12:12 | [maml_trainer] epoch #391 | EpochTime 1726.30 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.013 +Average/AverageReturn -51.8774 +Average/Iteration 391 +Average/MaxReturn -44.1592 +Average/MinReturn -80.1579 +Average/NumEpisodes 120 +Average/StdReturn 5.68098 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73368 +GaussianMLPPolicy/KLAfter 0.00435495 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.67266e-05 +GaussianMLPPolicy/LossBefore 2.14577e-08 +GaussianMLPPolicy/dLoss 8.6748e-05 +Iteration 391 +MetaTest/Average/AverageDiscountedReturn -55.3498 +MetaTest/Average/AverageReturn -55.3498 +MetaTest/Average/Iteration 391 +MetaTest/Average/MaxReturn -45.0201 +MetaTest/Average/MinReturn -125.606 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.8295 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3498 +MetaTest/__unnamed_task__/AverageReturn -55.3498 +MetaTest/__unnamed_task__/Iteration 391 +MetaTest/__unnamed_task__/MaxReturn -45.0201 +MetaTest/__unnamed_task__/MinReturn -125.606 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.8295 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8816e+07 +__unnamed_task__/AverageDiscountedReturn -27.013 +__unnamed_task__/AverageReturn -51.8774 +__unnamed_task__/Iteration 391 +__unnamed_task__/MaxReturn -44.1592 +__unnamed_task__/MinReturn -80.1579 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.68098 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 15:36:38 | [maml_trainer] epoch #392 | Sampling for adapation and meta-testing... +2025-04-11 15:40:40 | [maml_trainer] epoch #392 | Finished meta-testing... +2025-04-11 15:40:40 | [maml_trainer] epoch #392 | Saving snapshot... +2025-04-11 15:41:03 | [maml_trainer] epoch #392 | Saved +2025-04-11 15:41:03 | [maml_trainer] epoch #392 | Time 687707.02 s +2025-04-11 15:41:03 | [maml_trainer] epoch #392 | EpochTime 1730.90 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.9397 +Average/AverageReturn -51.8827 +Average/Iteration 392 +Average/MaxReturn -43.7292 +Average/MinReturn -105.884 +Average/NumEpisodes 120 +Average/StdReturn 6.67461 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73314 +GaussianMLPPolicy/KLAfter 0.00646529 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000102499 +GaussianMLPPolicy/LossBefore -3.21865e-09 +GaussianMLPPolicy/dLoss -0.000102502 +Iteration 392 +MetaTest/Average/AverageDiscountedReturn -52.552 +MetaTest/Average/AverageReturn -52.552 +MetaTest/Average/Iteration 392 +MetaTest/Average/MaxReturn -45.4695 +MetaTest/Average/MinReturn -63.3216 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.49635 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.552 +MetaTest/__unnamed_task__/AverageReturn -52.552 +MetaTest/__unnamed_task__/Iteration 392 +MetaTest/__unnamed_task__/MaxReturn -45.4695 +MetaTest/__unnamed_task__/MinReturn -63.3216 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.49635 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8864e+07 +__unnamed_task__/AverageDiscountedReturn -26.9397 +__unnamed_task__/AverageReturn -51.8827 +__unnamed_task__/Iteration 392 +__unnamed_task__/MaxReturn -43.7292 +__unnamed_task__/MinReturn -105.884 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.67461 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 16:05:35 | [maml_trainer] epoch #393 | Sampling for adapation and meta-testing... +2025-04-11 16:09:41 | [maml_trainer] epoch #393 | Finished meta-testing... +2025-04-11 16:09:41 | [maml_trainer] epoch #393 | Saving snapshot... +2025-04-11 16:10:03 | [maml_trainer] epoch #393 | Saved +2025-04-11 16:10:03 | [maml_trainer] epoch #393 | Time 689447.85 s +2025-04-11 16:10:03 | [maml_trainer] epoch #393 | EpochTime 1740.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.0715 +Average/AverageReturn -51.7885 +Average/Iteration 393 +Average/MaxReturn -43.2708 +Average/MinReturn -66.8631 +Average/NumEpisodes 120 +Average/StdReturn 4.7168 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73272 +GaussianMLPPolicy/KLAfter 0.00788474 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000246897 +GaussianMLPPolicy/LossBefore 9.21885e-09 +GaussianMLPPolicy/dLoss -0.000246888 +Iteration 393 +MetaTest/Average/AverageDiscountedReturn -51.6784 +MetaTest/Average/AverageReturn -51.6784 +MetaTest/Average/Iteration 393 +MetaTest/Average/MaxReturn -45.5049 +MetaTest/Average/MinReturn -63.5259 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.02267 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6784 +MetaTest/__unnamed_task__/AverageReturn -51.6784 +MetaTest/__unnamed_task__/Iteration 393 +MetaTest/__unnamed_task__/MaxReturn -45.5049 +MetaTest/__unnamed_task__/MinReturn -63.5259 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.02267 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.8912e+07 +__unnamed_task__/AverageDiscountedReturn -27.0715 +__unnamed_task__/AverageReturn -51.7885 +__unnamed_task__/Iteration 393 +__unnamed_task__/MaxReturn -43.2708 +__unnamed_task__/MinReturn -66.8631 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.7168 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 16:34:31 | [maml_trainer] epoch #394 | Sampling for adapation and meta-testing... +2025-04-11 16:38:38 | [maml_trainer] epoch #394 | Finished meta-testing... +2025-04-11 16:38:38 | [maml_trainer] epoch #394 | Saving snapshot... +2025-04-11 16:39:00 | [maml_trainer] epoch #394 | Saved +2025-04-11 16:39:00 | [maml_trainer] epoch #394 | Time 691184.33 s +2025-04-11 16:39:00 | [maml_trainer] epoch #394 | EpochTime 1736.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2483 +Average/AverageReturn -52.1995 +Average/Iteration 394 +Average/MaxReturn -44.7898 +Average/MinReturn -74.3169 +Average/NumEpisodes 120 +Average/StdReturn 4.92085 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73151 +GaussianMLPPolicy/KLAfter 0.00635341 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.64412e-05 +GaussianMLPPolicy/LossBefore 8.66254e-09 +GaussianMLPPolicy/dLoss 1.64498e-05 +Iteration 394 +MetaTest/Average/AverageDiscountedReturn -52.4885 +MetaTest/Average/AverageReturn -52.4885 +MetaTest/Average/Iteration 394 +MetaTest/Average/MaxReturn -46.5304 +MetaTest/Average/MinReturn -66.7444 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.09415 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.4885 +MetaTest/__unnamed_task__/AverageReturn -52.4885 +MetaTest/__unnamed_task__/Iteration 394 +MetaTest/__unnamed_task__/MaxReturn -46.5304 +MetaTest/__unnamed_task__/MinReturn -66.7444 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.09415 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.896e+07 +__unnamed_task__/AverageDiscountedReturn -27.2483 +__unnamed_task__/AverageReturn -52.1995 +__unnamed_task__/Iteration 394 +__unnamed_task__/MaxReturn -44.7898 +__unnamed_task__/MinReturn -74.3169 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.92085 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 17:03:29 | [maml_trainer] epoch #395 | Sampling for adapation and meta-testing... +2025-04-11 17:07:36 | [maml_trainer] epoch #395 | Finished meta-testing... +2025-04-11 17:07:36 | [maml_trainer] epoch #395 | Saving snapshot... +2025-04-11 17:07:57 | [maml_trainer] epoch #395 | Saved +2025-04-11 17:07:57 | [maml_trainer] epoch #395 | Time 692921.49 s +2025-04-11 17:07:57 | [maml_trainer] epoch #395 | EpochTime 1737.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -27.2975 +Average/AverageReturn -53.0207 +Average/Iteration 395 +Average/MaxReturn -43.6633 +Average/MinReturn -119.772 +Average/NumEpisodes 120 +Average/StdReturn 8.57364 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.73033 +GaussianMLPPolicy/KLAfter 0.006482 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000182348 +GaussianMLPPolicy/LossBefore -1.15236e-08 +GaussianMLPPolicy/dLoss -0.00018236 +Iteration 395 +MetaTest/Average/AverageDiscountedReturn -52.347 +MetaTest/Average/AverageReturn -52.347 +MetaTest/Average/Iteration 395 +MetaTest/Average/MaxReturn -43.4679 +MetaTest/Average/MinReturn -64.8107 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.1214 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.347 +MetaTest/__unnamed_task__/AverageReturn -52.347 +MetaTest/__unnamed_task__/Iteration 395 +MetaTest/__unnamed_task__/MaxReturn -43.4679 +MetaTest/__unnamed_task__/MinReturn -64.8107 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.1214 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9008e+07 +__unnamed_task__/AverageDiscountedReturn -27.2975 +__unnamed_task__/AverageReturn -53.0207 +__unnamed_task__/Iteration 395 +__unnamed_task__/MaxReturn -43.6633 +__unnamed_task__/MinReturn -119.772 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.57364 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 17:32:38 | [maml_trainer] epoch #396 | Sampling for adapation and meta-testing... +2025-04-11 17:36:41 | [maml_trainer] epoch #396 | Finished meta-testing... +2025-04-11 17:36:41 | [maml_trainer] epoch #396 | Saving snapshot... +2025-04-11 17:37:02 | [maml_trainer] epoch #396 | Saved +2025-04-11 17:37:02 | [maml_trainer] epoch #396 | Time 694666.29 s +2025-04-11 17:37:02 | [maml_trainer] epoch #396 | EpochTime 1744.80 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.9791 +Average/AverageReturn -52.0137 +Average/Iteration 396 +Average/MaxReturn -42.9795 +Average/MinReturn -69.0029 +Average/NumEpisodes 120 +Average/StdReturn 5.14976 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72864 +GaussianMLPPolicy/KLAfter 0.00525604 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.92448e-05 +GaussianMLPPolicy/LossBefore -1.45435e-08 +GaussianMLPPolicy/dLoss 4.92303e-05 +Iteration 396 +MetaTest/Average/AverageDiscountedReturn -55.2883 +MetaTest/Average/AverageReturn -55.2883 +MetaTest/Average/Iteration 396 +MetaTest/Average/MaxReturn -46.0096 +MetaTest/Average/MinReturn -102.656 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.1481 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.2883 +MetaTest/__unnamed_task__/AverageReturn -55.2883 +MetaTest/__unnamed_task__/Iteration 396 +MetaTest/__unnamed_task__/MaxReturn -46.0096 +MetaTest/__unnamed_task__/MinReturn -102.656 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.1481 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9056e+07 +__unnamed_task__/AverageDiscountedReturn -26.9791 +__unnamed_task__/AverageReturn -52.0137 +__unnamed_task__/Iteration 396 +__unnamed_task__/MaxReturn -42.9795 +__unnamed_task__/MinReturn -69.0029 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.14976 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 18:01:32 | [maml_trainer] epoch #397 | Sampling for adapation and meta-testing... +2025-04-11 18:05:39 | [maml_trainer] epoch #397 | Finished meta-testing... +2025-04-11 18:05:39 | [maml_trainer] epoch #397 | Saving snapshot... +2025-04-11 18:06:01 | [maml_trainer] epoch #397 | Saved +2025-04-11 18:06:01 | [maml_trainer] epoch #397 | Time 696405.14 s +2025-04-11 18:06:01 | [maml_trainer] epoch #397 | EpochTime 1738.84 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.848 +Average/AverageReturn -52.3357 +Average/Iteration 397 +Average/MaxReturn -44.1921 +Average/MinReturn -152.213 +Average/NumEpisodes 120 +Average/StdReturn 10.1666 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72599 +GaussianMLPPolicy/KLAfter 0.00415391 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.05384e-05 +GaussianMLPPolicy/LossBefore -1.1921e-10 +GaussianMLPPolicy/dLoss -1.05385e-05 +Iteration 397 +MetaTest/Average/AverageDiscountedReturn -52.1024 +MetaTest/Average/AverageReturn -52.1024 +MetaTest/Average/Iteration 397 +MetaTest/Average/MaxReturn -45.3573 +MetaTest/Average/MinReturn -61.7407 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.80982 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.1024 +MetaTest/__unnamed_task__/AverageReturn -52.1024 +MetaTest/__unnamed_task__/Iteration 397 +MetaTest/__unnamed_task__/MaxReturn -45.3573 +MetaTest/__unnamed_task__/MinReturn -61.7407 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.80982 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9104e+07 +__unnamed_task__/AverageDiscountedReturn -26.848 +__unnamed_task__/AverageReturn -52.3357 +__unnamed_task__/Iteration 397 +__unnamed_task__/MaxReturn -44.1921 +__unnamed_task__/MinReturn -152.213 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.1666 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 18:30:36 | [maml_trainer] epoch #398 | Sampling for adapation and meta-testing... +2025-04-11 18:34:42 | [maml_trainer] epoch #398 | Finished meta-testing... +2025-04-11 18:34:42 | [maml_trainer] epoch #398 | Saving snapshot... +2025-04-11 18:35:03 | [maml_trainer] epoch #398 | Saved +2025-04-11 18:35:03 | [maml_trainer] epoch #398 | Time 698147.16 s +2025-04-11 18:35:03 | [maml_trainer] epoch #398 | EpochTime 1742.02 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.7678 +Average/AverageReturn -52.1131 +Average/Iteration 398 +Average/MaxReturn -45.2007 +Average/MinReturn -69.8016 +Average/NumEpisodes 120 +Average/StdReturn 4.79912 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72511 +GaussianMLPPolicy/KLAfter 0.00249132 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.43641e-06 +GaussianMLPPolicy/LossBefore -7.3115e-09 +GaussianMLPPolicy/dLoss 4.4291e-06 +Iteration 398 +MetaTest/Average/AverageDiscountedReturn -54.1859 +MetaTest/Average/AverageReturn -54.1859 +MetaTest/Average/Iteration 398 +MetaTest/Average/MaxReturn -44.7434 +MetaTest/Average/MinReturn -75.1405 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.16882 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.1859 +MetaTest/__unnamed_task__/AverageReturn -54.1859 +MetaTest/__unnamed_task__/Iteration 398 +MetaTest/__unnamed_task__/MaxReturn -44.7434 +MetaTest/__unnamed_task__/MinReturn -75.1405 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.16882 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9152e+07 +__unnamed_task__/AverageDiscountedReturn -26.7678 +__unnamed_task__/AverageReturn -52.1131 +__unnamed_task__/Iteration 398 +__unnamed_task__/MaxReturn -45.2007 +__unnamed_task__/MinReturn -69.8016 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.79912 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 18:59:44 | [maml_trainer] epoch #399 | Sampling for adapation and meta-testing... +2025-04-11 19:03:55 | [maml_trainer] epoch #399 | Finished meta-testing... +2025-04-11 19:03:55 | [maml_trainer] epoch #399 | Saving snapshot... +2025-04-11 19:04:17 | [maml_trainer] epoch #399 | Saved +2025-04-11 19:04:17 | [maml_trainer] epoch #399 | Time 699901.48 s +2025-04-11 19:04:17 | [maml_trainer] epoch #399 | EpochTime 1754.31 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2784 +Average/AverageReturn -53.4214 +Average/Iteration 399 +Average/MaxReturn -42.5207 +Average/MinReturn -91.5584 +Average/NumEpisodes 120 +Average/StdReturn 7.00915 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72487 +GaussianMLPPolicy/KLAfter 0.00333151 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.09426e-05 +GaussianMLPPolicy/LossBefore 1.29143e-08 +GaussianMLPPolicy/dLoss -6.09297e-05 +Iteration 399 +MetaTest/Average/AverageDiscountedReturn -52.8459 +MetaTest/Average/AverageReturn -52.8459 +MetaTest/Average/Iteration 399 +MetaTest/Average/MaxReturn -44.4622 +MetaTest/Average/MinReturn -69.5019 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.60119 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.8459 +MetaTest/__unnamed_task__/AverageReturn -52.8459 +MetaTest/__unnamed_task__/Iteration 399 +MetaTest/__unnamed_task__/MaxReturn -44.4622 +MetaTest/__unnamed_task__/MinReturn -69.5019 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.60119 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.92e+07 +__unnamed_task__/AverageDiscountedReturn -27.2784 +__unnamed_task__/AverageReturn -53.4214 +__unnamed_task__/Iteration 399 +__unnamed_task__/MaxReturn -42.5207 +__unnamed_task__/MinReturn -91.5584 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.00915 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 19:28:55 | [maml_trainer] epoch #400 | Sampling for adapation and meta-testing... +2025-04-11 19:32:59 | [maml_trainer] epoch #400 | Finished meta-testing... +2025-04-11 19:32:59 | [maml_trainer] epoch #400 | Saving snapshot... +2025-04-11 19:33:20 | [maml_trainer] epoch #400 | Saved +2025-04-11 19:33:20 | [maml_trainer] epoch #400 | Time 701644.36 s +2025-04-11 19:33:20 | [maml_trainer] epoch #400 | EpochTime 1742.88 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -27.2167 +Average/AverageReturn -52.8298 +Average/Iteration 400 +Average/MaxReturn -44.0011 +Average/MinReturn -68.2693 +Average/NumEpisodes 120 +Average/StdReturn 5.42342 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72484 +GaussianMLPPolicy/KLAfter 0.00341866 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.88008e-05 +GaussianMLPPolicy/LossBefore 1.03315e-09 +GaussianMLPPolicy/dLoss 6.88018e-05 +Iteration 400 +MetaTest/Average/AverageDiscountedReturn -51.729 +MetaTest/Average/AverageReturn -51.729 +MetaTest/Average/Iteration 400 +MetaTest/Average/MaxReturn -45.3076 +MetaTest/Average/MinReturn -62.3369 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.46671 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.729 +MetaTest/__unnamed_task__/AverageReturn -51.729 +MetaTest/__unnamed_task__/Iteration 400 +MetaTest/__unnamed_task__/MaxReturn -45.3076 +MetaTest/__unnamed_task__/MinReturn -62.3369 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.46671 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9248e+07 +__unnamed_task__/AverageDiscountedReturn -27.2167 +__unnamed_task__/AverageReturn -52.8298 +__unnamed_task__/Iteration 400 +__unnamed_task__/MaxReturn -44.0011 +__unnamed_task__/MinReturn -68.2693 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.42342 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 19:57:43 | [maml_trainer] epoch #401 | Sampling for adapation and meta-testing... +2025-04-11 20:01:48 | [maml_trainer] epoch #401 | Finished meta-testing... +2025-04-11 20:01:48 | [maml_trainer] epoch #401 | Saving snapshot... +2025-04-11 20:02:10 | [maml_trainer] epoch #401 | Saved +2025-04-11 20:02:10 | [maml_trainer] epoch #401 | Time 703374.86 s +2025-04-11 20:02:10 | [maml_trainer] epoch #401 | EpochTime 1730.50 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.5341 +Average/AverageReturn -51.1387 +Average/Iteration 401 +Average/MaxReturn -43.9647 +Average/MinReturn -65.1325 +Average/NumEpisodes 120 +Average/StdReturn 4.27271 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72371 +GaussianMLPPolicy/KLAfter 0.00502229 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.45049e-05 +GaussianMLPPolicy/LossBefore 1.63714e-08 +GaussianMLPPolicy/dLoss 7.45213e-05 +Iteration 401 +MetaTest/Average/AverageDiscountedReturn -50.5974 +MetaTest/Average/AverageReturn -50.5974 +MetaTest/Average/Iteration 401 +MetaTest/Average/MaxReturn -44.3238 +MetaTest/Average/MinReturn -57.6279 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.89318 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.5974 +MetaTest/__unnamed_task__/AverageReturn -50.5974 +MetaTest/__unnamed_task__/Iteration 401 +MetaTest/__unnamed_task__/MaxReturn -44.3238 +MetaTest/__unnamed_task__/MinReturn -57.6279 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.89318 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9296e+07 +__unnamed_task__/AverageDiscountedReturn -26.5341 +__unnamed_task__/AverageReturn -51.1387 +__unnamed_task__/Iteration 401 +__unnamed_task__/MaxReturn -43.9647 +__unnamed_task__/MinReturn -65.1325 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.27271 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 20:26:41 | [maml_trainer] epoch #402 | Sampling for adapation and meta-testing... +2025-04-11 20:30:47 | [maml_trainer] epoch #402 | Finished meta-testing... +2025-04-11 20:30:47 | [maml_trainer] epoch #402 | Saving snapshot... +2025-04-11 20:31:09 | [maml_trainer] epoch #402 | Saved +2025-04-11 20:31:09 | [maml_trainer] epoch #402 | Time 705113.27 s +2025-04-11 20:31:09 | [maml_trainer] epoch #402 | EpochTime 1738.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.6874 +Average/AverageReturn -51.1824 +Average/Iteration 402 +Average/MaxReturn -42.3631 +Average/MinReturn -67.5592 +Average/NumEpisodes 120 +Average/StdReturn 4.87778 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72228 +GaussianMLPPolicy/KLAfter 0.00429981 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000129729 +GaussianMLPPolicy/LossBefore -8.1857e-09 +GaussianMLPPolicy/dLoss 0.00012972 +Iteration 402 +MetaTest/Average/AverageDiscountedReturn -51.2657 +MetaTest/Average/AverageReturn -51.2657 +MetaTest/Average/Iteration 402 +MetaTest/Average/MaxReturn -44.629 +MetaTest/Average/MinReturn -63.7477 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.76892 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.2657 +MetaTest/__unnamed_task__/AverageReturn -51.2657 +MetaTest/__unnamed_task__/Iteration 402 +MetaTest/__unnamed_task__/MaxReturn -44.629 +MetaTest/__unnamed_task__/MinReturn -63.7477 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.76892 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9344e+07 +__unnamed_task__/AverageDiscountedReturn -26.6874 +__unnamed_task__/AverageReturn -51.1824 +__unnamed_task__/Iteration 402 +__unnamed_task__/MaxReturn -42.3631 +__unnamed_task__/MinReturn -67.5592 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.87778 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 20:55:58 | [maml_trainer] epoch #403 | Sampling for adapation and meta-testing... +2025-04-11 21:00:05 | [maml_trainer] epoch #403 | Finished meta-testing... +2025-04-11 21:00:05 | [maml_trainer] epoch #403 | Saving snapshot... +2025-04-11 21:00:26 | [maml_trainer] epoch #403 | Saved +2025-04-11 21:00:26 | [maml_trainer] epoch #403 | Time 706870.65 s +2025-04-11 21:00:26 | [maml_trainer] epoch #403 | EpochTime 1757.38 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.7361 +Average/AverageReturn -51.3556 +Average/Iteration 403 +Average/MaxReturn -44.0173 +Average/MinReturn -74.4358 +Average/NumEpisodes 120 +Average/StdReturn 4.74206 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.72112 +GaussianMLPPolicy/KLAfter 0.00268456 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000105203 +GaussianMLPPolicy/LossBefore -2.03451e-08 +GaussianMLPPolicy/dLoss 0.000105182 +Iteration 403 +MetaTest/Average/AverageDiscountedReturn -51.4008 +MetaTest/Average/AverageReturn -51.4008 +MetaTest/Average/Iteration 403 +MetaTest/Average/MaxReturn -44.9982 +MetaTest/Average/MinReturn -59.5969 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.97409 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.4008 +MetaTest/__unnamed_task__/AverageReturn -51.4008 +MetaTest/__unnamed_task__/Iteration 403 +MetaTest/__unnamed_task__/MaxReturn -44.9982 +MetaTest/__unnamed_task__/MinReturn -59.5969 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.97409 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9392e+07 +__unnamed_task__/AverageDiscountedReturn -26.7361 +__unnamed_task__/AverageReturn -51.3556 +__unnamed_task__/Iteration 403 +__unnamed_task__/MaxReturn -44.0173 +__unnamed_task__/MinReturn -74.4358 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.74206 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 21:25:20 | [maml_trainer] epoch #404 | Sampling for adapation and meta-testing... +2025-04-11 21:29:31 | [maml_trainer] epoch #404 | Finished meta-testing... +2025-04-11 21:29:31 | [maml_trainer] epoch #404 | Saving snapshot... +2025-04-11 21:29:53 | [maml_trainer] epoch #404 | Saved +2025-04-11 21:29:53 | [maml_trainer] epoch #404 | Time 708637.65 s +2025-04-11 21:29:53 | [maml_trainer] epoch #404 | EpochTime 1766.99 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.5992 +Average/AverageReturn -51.321 +Average/Iteration 404 +Average/MaxReturn -42.8712 +Average/MinReturn -148.605 +Average/NumEpisodes 120 +Average/StdReturn 9.77794 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.71989 +GaussianMLPPolicy/KLAfter 0.002695 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.95195e-05 +GaussianMLPPolicy/LossBefore -1.40667e-08 +GaussianMLPPolicy/dLoss -9.95336e-05 +Iteration 404 +MetaTest/Average/AverageDiscountedReturn -49.5972 +MetaTest/Average/AverageReturn -49.5972 +MetaTest/Average/Iteration 404 +MetaTest/Average/MaxReturn -42.8999 +MetaTest/Average/MinReturn -57.483 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.89641 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5972 +MetaTest/__unnamed_task__/AverageReturn -49.5972 +MetaTest/__unnamed_task__/Iteration 404 +MetaTest/__unnamed_task__/MaxReturn -42.8999 +MetaTest/__unnamed_task__/MinReturn -57.483 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.89641 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.944e+07 +__unnamed_task__/AverageDiscountedReturn -26.5992 +__unnamed_task__/AverageReturn -51.321 +__unnamed_task__/Iteration 404 +__unnamed_task__/MaxReturn -42.8712 +__unnamed_task__/MinReturn -148.605 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.77794 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 21:54:53 | [maml_trainer] epoch #405 | Sampling for adapation and meta-testing... +2025-04-11 21:59:01 | [maml_trainer] epoch #405 | Finished meta-testing... +2025-04-11 21:59:01 | [maml_trainer] epoch #405 | Saving snapshot... +2025-04-11 21:59:23 | [maml_trainer] epoch #405 | Saved +2025-04-11 21:59:23 | [maml_trainer] epoch #405 | Time 710407.82 s +2025-04-11 21:59:23 | [maml_trainer] epoch #405 | EpochTime 1770.17 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.043 +Average/AverageReturn -49.7134 +Average/Iteration 405 +Average/MaxReturn -42.2228 +Average/MinReturn -67.6647 +Average/NumEpisodes 120 +Average/StdReturn 3.98018 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.71769 +GaussianMLPPolicy/KLAfter 0.00222343 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.57218e-05 +GaussianMLPPolicy/LossBefore 1.49409e-08 +GaussianMLPPolicy/dLoss 6.57367e-05 +Iteration 405 +MetaTest/Average/AverageDiscountedReturn -49.8093 +MetaTest/Average/AverageReturn -49.8093 +MetaTest/Average/Iteration 405 +MetaTest/Average/MaxReturn -44.7462 +MetaTest/Average/MinReturn -56.9459 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.80524 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8093 +MetaTest/__unnamed_task__/AverageReturn -49.8093 +MetaTest/__unnamed_task__/Iteration 405 +MetaTest/__unnamed_task__/MaxReturn -44.7462 +MetaTest/__unnamed_task__/MinReturn -56.9459 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.80524 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9488e+07 +__unnamed_task__/AverageDiscountedReturn -26.043 +__unnamed_task__/AverageReturn -49.7134 +__unnamed_task__/Iteration 405 +__unnamed_task__/MaxReturn -42.2228 +__unnamed_task__/MinReturn -67.6647 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 3.98018 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 22:24:50 | [maml_trainer] epoch #406 | Sampling for adapation and meta-testing... +2025-04-11 22:29:03 | [maml_trainer] epoch #406 | Finished meta-testing... +2025-04-11 22:29:03 | [maml_trainer] epoch #406 | Saving snapshot... +2025-04-11 22:29:25 | [maml_trainer] epoch #406 | Saved +2025-04-11 22:29:25 | [maml_trainer] epoch #406 | Time 712209.82 s +2025-04-11 22:29:25 | [maml_trainer] epoch #406 | EpochTime 1802.00 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.9601 +Average/AverageReturn -49.2929 +Average/Iteration 406 +Average/MaxReturn -43.2377 +Average/MinReturn -63.1984 +Average/NumEpisodes 120 +Average/StdReturn 3.46093 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.71483 +GaussianMLPPolicy/KLAfter 0.00222272 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000139978 +GaussianMLPPolicy/LossBefore -2.28882e-08 +GaussianMLPPolicy/dLoss 0.000139956 +Iteration 406 +MetaTest/Average/AverageDiscountedReturn -49.9647 +MetaTest/Average/AverageReturn -49.9647 +MetaTest/Average/Iteration 406 +MetaTest/Average/MaxReturn -45.5664 +MetaTest/Average/MinReturn -55.9047 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.96144 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9647 +MetaTest/__unnamed_task__/AverageReturn -49.9647 +MetaTest/__unnamed_task__/Iteration 406 +MetaTest/__unnamed_task__/MaxReturn -45.5664 +MetaTest/__unnamed_task__/MinReturn -55.9047 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.96144 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9536e+07 +__unnamed_task__/AverageDiscountedReturn -25.9601 +__unnamed_task__/AverageReturn -49.2929 +__unnamed_task__/Iteration 406 +__unnamed_task__/MaxReturn -43.2377 +__unnamed_task__/MinReturn -63.1984 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 3.46093 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-11 22:54:20 | [maml_trainer] epoch #407 | Sampling for adapation and meta-testing... +2025-04-11 22:58:31 | [maml_trainer] epoch #407 | Finished meta-testing... +2025-04-11 22:58:31 | [maml_trainer] epoch #407 | Saving snapshot... +2025-04-11 22:58:52 | [maml_trainer] epoch #407 | Saved +2025-04-11 22:58:52 | [maml_trainer] epoch #407 | Time 713976.86 s +2025-04-11 22:58:52 | [maml_trainer] epoch #407 | EpochTime 1767.04 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.0649 +Average/AverageReturn -49.9898 +Average/Iteration 407 +Average/MaxReturn -43.5763 +Average/MinReturn -105.079 +Average/NumEpisodes 120 +Average/StdReturn 6.20756 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.71242 +GaussianMLPPolicy/KLAfter 0.00431086 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.91141e-05 +GaussianMLPPolicy/LossBefore -4.76837e-10 +GaussianMLPPolicy/dLoss 7.91136e-05 +Iteration 407 +MetaTest/Average/AverageDiscountedReturn -48.3891 +MetaTest/Average/AverageReturn -48.3891 +MetaTest/Average/Iteration 407 +MetaTest/Average/MaxReturn -41.736 +MetaTest/Average/MinReturn -60.9145 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.15222 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.3891 +MetaTest/__unnamed_task__/AverageReturn -48.3891 +MetaTest/__unnamed_task__/Iteration 407 +MetaTest/__unnamed_task__/MaxReturn -41.736 +MetaTest/__unnamed_task__/MinReturn -60.9145 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.15222 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9584e+07 +__unnamed_task__/AverageDiscountedReturn -26.0649 +__unnamed_task__/AverageReturn -49.9898 +__unnamed_task__/Iteration 407 +__unnamed_task__/MaxReturn -43.5763 +__unnamed_task__/MinReturn -105.079 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.20756 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 23:24:02 | [maml_trainer] epoch #408 | Sampling for adapation and meta-testing... +2025-04-11 23:28:12 | [maml_trainer] epoch #408 | Finished meta-testing... +2025-04-11 23:28:12 | [maml_trainer] epoch #408 | Saving snapshot... +2025-04-11 23:28:34 | [maml_trainer] epoch #408 | Saved +2025-04-11 23:28:34 | [maml_trainer] epoch #408 | Time 715758.83 s +2025-04-11 23:28:34 | [maml_trainer] epoch #408 | EpochTime 1781.96 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.1595 +Average/AverageReturn -49.9426 +Average/Iteration 408 +Average/MaxReturn -42.8164 +Average/MinReturn -114.148 +Average/NumEpisodes 120 +Average/StdReturn 7.30738 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.70962 +GaussianMLPPolicy/KLAfter 0.00794484 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.49872e-05 +GaussianMLPPolicy/LossBefore -5.5631e-09 +GaussianMLPPolicy/dLoss -6.49928e-05 +Iteration 408 +MetaTest/Average/AverageDiscountedReturn -48.9374 +MetaTest/Average/AverageReturn -48.9374 +MetaTest/Average/Iteration 408 +MetaTest/Average/MaxReturn -41.133 +MetaTest/Average/MinReturn -58.8875 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.0769 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9374 +MetaTest/__unnamed_task__/AverageReturn -48.9374 +MetaTest/__unnamed_task__/Iteration 408 +MetaTest/__unnamed_task__/MaxReturn -41.133 +MetaTest/__unnamed_task__/MinReturn -58.8875 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.0769 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9632e+07 +__unnamed_task__/AverageDiscountedReturn -26.1595 +__unnamed_task__/AverageReturn -49.9426 +__unnamed_task__/Iteration 408 +__unnamed_task__/MaxReturn -42.8164 +__unnamed_task__/MinReturn -114.148 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.30738 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-11 23:53:25 | [maml_trainer] epoch #409 | Sampling for adapation and meta-testing... +2025-04-11 23:57:31 | [maml_trainer] epoch #409 | Finished meta-testing... +2025-04-11 23:57:31 | [maml_trainer] epoch #409 | Saving snapshot... +2025-04-11 23:57:52 | [maml_trainer] epoch #409 | Saved +2025-04-11 23:57:52 | [maml_trainer] epoch #409 | Time 717516.92 s +2025-04-11 23:57:52 | [maml_trainer] epoch #409 | EpochTime 1758.09 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.2498 +Average/AverageReturn -49.7597 +Average/Iteration 409 +Average/MaxReturn -43.3303 +Average/MinReturn -67.9593 +Average/NumEpisodes 120 +Average/StdReturn 4.2085 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.70601 +GaussianMLPPolicy/KLAfter 0.00609624 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.72737e-05 +GaussianMLPPolicy/LossBefore 1.27157e-08 +GaussianMLPPolicy/dLoss 1.72865e-05 +Iteration 409 +MetaTest/Average/AverageDiscountedReturn -48.7964 +MetaTest/Average/AverageReturn -48.7964 +MetaTest/Average/Iteration 409 +MetaTest/Average/MaxReturn -42.131 +MetaTest/Average/MinReturn -61.309 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.49014 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.7964 +MetaTest/__unnamed_task__/AverageReturn -48.7964 +MetaTest/__unnamed_task__/Iteration 409 +MetaTest/__unnamed_task__/MaxReturn -42.131 +MetaTest/__unnamed_task__/MinReturn -61.309 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.49014 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.968e+07 +__unnamed_task__/AverageDiscountedReturn -26.2498 +__unnamed_task__/AverageReturn -49.7597 +__unnamed_task__/Iteration 409 +__unnamed_task__/MaxReturn -43.3303 +__unnamed_task__/MinReturn -67.9593 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.2085 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 00:22:34 | [maml_trainer] epoch #410 | Sampling for adapation and meta-testing... +2025-04-12 00:26:44 | [maml_trainer] epoch #410 | Finished meta-testing... +2025-04-12 00:26:44 | [maml_trainer] epoch #410 | Saving snapshot... +2025-04-12 00:27:05 | [maml_trainer] epoch #410 | Saved +2025-04-12 00:27:05 | [maml_trainer] epoch #410 | Time 719269.68 s +2025-04-12 00:27:05 | [maml_trainer] epoch #410 | EpochTime 1752.75 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.0749 +Average/AverageReturn -49.3678 +Average/Iteration 410 +Average/MaxReturn -42.596 +Average/MinReturn -64.3921 +Average/NumEpisodes 120 +Average/StdReturn 3.96236 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.70304 +GaussianMLPPolicy/KLAfter 0.00456303 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.7024e-05 +GaussianMLPPolicy/LossBefore -7.62939e-09 +GaussianMLPPolicy/dLoss 1.70163e-05 +Iteration 410 +MetaTest/Average/AverageDiscountedReturn -50.2222 +MetaTest/Average/AverageReturn -50.2222 +MetaTest/Average/Iteration 410 +MetaTest/Average/MaxReturn -41.7096 +MetaTest/Average/MinReturn -66.9103 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.09523 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2222 +MetaTest/__unnamed_task__/AverageReturn -50.2222 +MetaTest/__unnamed_task__/Iteration 410 +MetaTest/__unnamed_task__/MaxReturn -41.7096 +MetaTest/__unnamed_task__/MinReturn -66.9103 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.09523 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9728e+07 +__unnamed_task__/AverageDiscountedReturn -26.0749 +__unnamed_task__/AverageReturn -49.3678 +__unnamed_task__/Iteration 410 +__unnamed_task__/MaxReturn -42.596 +__unnamed_task__/MinReturn -64.3921 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 3.96236 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 00:52:07 | [maml_trainer] epoch #411 | Sampling for adapation and meta-testing... +2025-04-12 00:56:15 | [maml_trainer] epoch #411 | Finished meta-testing... +2025-04-12 00:56:15 | [maml_trainer] epoch #411 | Saving snapshot... +2025-04-12 00:56:37 | [maml_trainer] epoch #411 | Saved +2025-04-12 00:56:37 | [maml_trainer] epoch #411 | Time 721040.98 s +2025-04-12 00:56:37 | [maml_trainer] epoch #411 | EpochTime 1771.30 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -26.1171 +Average/AverageReturn -49.8206 +Average/Iteration 411 +Average/MaxReturn -41.3978 +Average/MinReturn -89.9209 +Average/NumEpisodes 120 +Average/StdReturn 5.36615 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69927 +GaussianMLPPolicy/KLAfter 0.00249786 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.32937e-05 +GaussianMLPPolicy/LossBefore 1.7484e-09 +GaussianMLPPolicy/dLoss 2.32954e-05 +Iteration 411 +MetaTest/Average/AverageDiscountedReturn -48.3262 +MetaTest/Average/AverageReturn -48.3262 +MetaTest/Average/Iteration 411 +MetaTest/Average/MaxReturn -43.5117 +MetaTest/Average/MinReturn -54.9406 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.93288 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.3262 +MetaTest/__unnamed_task__/AverageReturn -48.3262 +MetaTest/__unnamed_task__/Iteration 411 +MetaTest/__unnamed_task__/MaxReturn -43.5117 +MetaTest/__unnamed_task__/MinReturn -54.9406 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.93288 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9776e+07 +__unnamed_task__/AverageDiscountedReturn -26.1171 +__unnamed_task__/AverageReturn -49.8206 +__unnamed_task__/Iteration 411 +__unnamed_task__/MaxReturn -41.3978 +__unnamed_task__/MinReturn -89.9209 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.36615 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 01:21:27 | [maml_trainer] epoch #412 | Sampling for adapation and meta-testing... +2025-04-12 01:25:36 | [maml_trainer] epoch #412 | Finished meta-testing... +2025-04-12 01:25:36 | [maml_trainer] epoch #412 | Saving snapshot... +2025-04-12 01:25:57 | [maml_trainer] epoch #412 | Saved +2025-04-12 01:25:57 | [maml_trainer] epoch #412 | Time 722801.38 s +2025-04-12 01:25:57 | [maml_trainer] epoch #412 | EpochTime 1760.39 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.0192 +Average/AverageReturn -49.2314 +Average/Iteration 412 +Average/MaxReturn -40.9618 +Average/MinReturn -100.281 +Average/NumEpisodes 120 +Average/StdReturn 6.0238 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69652 +GaussianMLPPolicy/KLAfter 0.00338616 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.87846e-05 +GaussianMLPPolicy/LossBefore -1.16825e-08 +GaussianMLPPolicy/dLoss 7.87729e-05 +Iteration 412 +MetaTest/Average/AverageDiscountedReturn -50.1949 +MetaTest/Average/AverageReturn -50.1949 +MetaTest/Average/Iteration 412 +MetaTest/Average/MaxReturn -42.8192 +MetaTest/Average/MinReturn -62.5167 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.30909 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1949 +MetaTest/__unnamed_task__/AverageReturn -50.1949 +MetaTest/__unnamed_task__/Iteration 412 +MetaTest/__unnamed_task__/MaxReturn -42.8192 +MetaTest/__unnamed_task__/MinReturn -62.5167 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.30909 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9824e+07 +__unnamed_task__/AverageDiscountedReturn -26.0192 +__unnamed_task__/AverageReturn -49.2314 +__unnamed_task__/Iteration 412 +__unnamed_task__/MaxReturn -40.9618 +__unnamed_task__/MinReturn -100.281 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.0238 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 01:50:34 | [maml_trainer] epoch #413 | Sampling for adapation and meta-testing... +2025-04-12 01:54:47 | [maml_trainer] epoch #413 | Finished meta-testing... +2025-04-12 01:54:47 | [maml_trainer] epoch #413 | Saving snapshot... +2025-04-12 01:55:08 | [maml_trainer] epoch #413 | Saved +2025-04-12 01:55:08 | [maml_trainer] epoch #413 | Time 724552.93 s +2025-04-12 01:55:08 | [maml_trainer] epoch #413 | EpochTime 1751.54 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.6447 +Average/AverageReturn -48.5356 +Average/Iteration 413 +Average/MaxReturn -42.1924 +Average/MinReturn -73.2416 +Average/NumEpisodes 120 +Average/StdReturn 4.45418 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6937 +GaussianMLPPolicy/KLAfter 0.00289735 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.98184e-06 +GaussianMLPPolicy/LossBefore -3.25044e-08 +GaussianMLPPolicy/dLoss 4.94933e-06 +Iteration 413 +MetaTest/Average/AverageDiscountedReturn -48.5605 +MetaTest/Average/AverageReturn -48.5605 +MetaTest/Average/Iteration 413 +MetaTest/Average/MaxReturn -40.121 +MetaTest/Average/MinReturn -56.2503 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.91363 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.5605 +MetaTest/__unnamed_task__/AverageReturn -48.5605 +MetaTest/__unnamed_task__/Iteration 413 +MetaTest/__unnamed_task__/MaxReturn -40.121 +MetaTest/__unnamed_task__/MinReturn -56.2503 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.91363 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9872e+07 +__unnamed_task__/AverageDiscountedReturn -25.6447 +__unnamed_task__/AverageReturn -48.5356 +__unnamed_task__/Iteration 413 +__unnamed_task__/MaxReturn -42.1924 +__unnamed_task__/MinReturn -73.2416 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.45418 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 02:19:57 | [maml_trainer] epoch #414 | Sampling for adapation and meta-testing... +2025-04-12 02:24:06 | [maml_trainer] epoch #414 | Finished meta-testing... +2025-04-12 02:24:06 | [maml_trainer] epoch #414 | Saving snapshot... +2025-04-12 02:24:28 | [maml_trainer] epoch #414 | Saved +2025-04-12 02:24:28 | [maml_trainer] epoch #414 | Time 726312.28 s +2025-04-12 02:24:28 | [maml_trainer] epoch #414 | EpochTime 1759.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.6798 +Average/AverageReturn -48.5631 +Average/Iteration 414 +Average/MaxReturn -40.6723 +Average/MinReturn -65.6389 +Average/NumEpisodes 120 +Average/StdReturn 4.287 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69174 +GaussianMLPPolicy/KLAfter 0.0028878 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.23391e-05 +GaussianMLPPolicy/LossBefore 1.38283e-08 +GaussianMLPPolicy/dLoss 4.23529e-05 +Iteration 414 +MetaTest/Average/AverageDiscountedReturn -48.6917 +MetaTest/Average/AverageReturn -48.6917 +MetaTest/Average/Iteration 414 +MetaTest/Average/MaxReturn -40.7698 +MetaTest/Average/MinReturn -57.8856 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.74015 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6917 +MetaTest/__unnamed_task__/AverageReturn -48.6917 +MetaTest/__unnamed_task__/Iteration 414 +MetaTest/__unnamed_task__/MaxReturn -40.7698 +MetaTest/__unnamed_task__/MinReturn -57.8856 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.74015 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.992e+07 +__unnamed_task__/AverageDiscountedReturn -25.6798 +__unnamed_task__/AverageReturn -48.5631 +__unnamed_task__/Iteration 414 +__unnamed_task__/MaxReturn -40.6723 +__unnamed_task__/MinReturn -65.6389 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.287 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 02:49:15 | [maml_trainer] epoch #415 | Sampling for adapation and meta-testing... +2025-04-12 02:53:23 | [maml_trainer] epoch #415 | Finished meta-testing... +2025-04-12 02:53:23 | [maml_trainer] epoch #415 | Saving snapshot... +2025-04-12 02:53:45 | [maml_trainer] epoch #415 | Saved +2025-04-12 02:53:45 | [maml_trainer] epoch #415 | Time 728069.94 s +2025-04-12 02:53:45 | [maml_trainer] epoch #415 | EpochTime 1757.66 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.9407 +Average/AverageReturn -49.3099 +Average/Iteration 415 +Average/MaxReturn -40.0121 +Average/MinReturn -70.5578 +Average/NumEpisodes 120 +Average/StdReturn 5.25371 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69083 +GaussianMLPPolicy/KLAfter 0.00250219 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.93705e-06 +GaussianMLPPolicy/LossBefore -8.42412e-09 +GaussianMLPPolicy/dLoss 3.92862e-06 +Iteration 415 +MetaTest/Average/AverageDiscountedReturn -48.9318 +MetaTest/Average/AverageReturn -48.9318 +MetaTest/Average/Iteration 415 +MetaTest/Average/MaxReturn -40.295 +MetaTest/Average/MinReturn -63.7715 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.59946 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.9318 +MetaTest/__unnamed_task__/AverageReturn -48.9318 +MetaTest/__unnamed_task__/Iteration 415 +MetaTest/__unnamed_task__/MaxReturn -40.295 +MetaTest/__unnamed_task__/MinReturn -63.7715 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.59946 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 1.9968e+07 +__unnamed_task__/AverageDiscountedReturn -25.9407 +__unnamed_task__/AverageReturn -49.3099 +__unnamed_task__/Iteration 415 +__unnamed_task__/MaxReturn -40.0121 +__unnamed_task__/MinReturn -70.5578 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.25371 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 03:18:15 | [maml_trainer] epoch #416 | Sampling for adapation and meta-testing... +2025-04-12 03:22:18 | [maml_trainer] epoch #416 | Finished meta-testing... +2025-04-12 03:22:18 | [maml_trainer] epoch #416 | Saving snapshot... +2025-04-12 03:22:39 | [maml_trainer] epoch #416 | Saved +2025-04-12 03:22:39 | [maml_trainer] epoch #416 | Time 729803.27 s +2025-04-12 03:22:39 | [maml_trainer] epoch #416 | EpochTime 1733.33 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.9196 +Average/AverageReturn -49.2299 +Average/Iteration 416 +Average/MaxReturn -41.587 +Average/MinReturn -72.0537 +Average/NumEpisodes 120 +Average/StdReturn 5.1897 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68893 +GaussianMLPPolicy/KLAfter 0.00145986 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.09366e-06 +GaussianMLPPolicy/LossBefore -8.74202e-10 +GaussianMLPPolicy/dLoss -6.09454e-06 +Iteration 416 +MetaTest/Average/AverageDiscountedReturn -48.5987 +MetaTest/Average/AverageReturn -48.5987 +MetaTest/Average/Iteration 416 +MetaTest/Average/MaxReturn -39.5893 +MetaTest/Average/MinReturn -62.4714 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.18019 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.5987 +MetaTest/__unnamed_task__/AverageReturn -48.5987 +MetaTest/__unnamed_task__/Iteration 416 +MetaTest/__unnamed_task__/MaxReturn -39.5893 +MetaTest/__unnamed_task__/MinReturn -62.4714 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.18019 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0016e+07 +__unnamed_task__/AverageDiscountedReturn -25.9196 +__unnamed_task__/AverageReturn -49.2299 +__unnamed_task__/Iteration 416 +__unnamed_task__/MaxReturn -41.587 +__unnamed_task__/MinReturn -72.0537 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.1897 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 03:46:52 | [maml_trainer] epoch #417 | Sampling for adapation and meta-testing... +2025-04-12 03:50:53 | [maml_trainer] epoch #417 | Finished meta-testing... +2025-04-12 03:50:53 | [maml_trainer] epoch #417 | Saving snapshot... +2025-04-12 03:51:14 | [maml_trainer] epoch #417 | Saved +2025-04-12 03:51:14 | [maml_trainer] epoch #417 | Time 731518.67 s +2025-04-12 03:51:14 | [maml_trainer] epoch #417 | EpochTime 1715.40 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.2946 +Average/AverageReturn -47.7387 +Average/Iteration 417 +Average/MaxReturn -39.5605 +Average/MinReturn -69.5652 +Average/NumEpisodes 120 +Average/StdReturn 4.51208 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6866 +GaussianMLPPolicy/KLAfter 0.00183537 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.83242e-05 +GaussianMLPPolicy/LossBefore -7.78834e-09 +GaussianMLPPolicy/dLoss -6.8332e-05 +Iteration 417 +MetaTest/Average/AverageDiscountedReturn -50.9015 +MetaTest/Average/AverageReturn -50.9015 +MetaTest/Average/Iteration 417 +MetaTest/Average/MaxReturn -41.5113 +MetaTest/Average/MinReturn -77.2844 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.62928 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.9015 +MetaTest/__unnamed_task__/AverageReturn -50.9015 +MetaTest/__unnamed_task__/Iteration 417 +MetaTest/__unnamed_task__/MaxReturn -41.5113 +MetaTest/__unnamed_task__/MinReturn -77.2844 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.62928 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0064e+07 +__unnamed_task__/AverageDiscountedReturn -25.2946 +__unnamed_task__/AverageReturn -47.7387 +__unnamed_task__/Iteration 417 +__unnamed_task__/MaxReturn -39.5605 +__unnamed_task__/MinReturn -69.5652 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.51208 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 04:15:58 | [maml_trainer] epoch #418 | Sampling for adapation and meta-testing... +2025-04-12 04:20:01 | [maml_trainer] epoch #418 | Finished meta-testing... +2025-04-12 04:20:01 | [maml_trainer] epoch #418 | Saving snapshot... +2025-04-12 04:20:23 | [maml_trainer] epoch #418 | Saved +2025-04-12 04:20:23 | [maml_trainer] epoch #418 | Time 733267.94 s +2025-04-12 04:20:23 | [maml_trainer] epoch #418 | EpochTime 1749.27 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -26.0981 +Average/AverageReturn -49.8901 +Average/Iteration 418 +Average/MaxReturn -39.8408 +Average/MinReturn -72.5622 +Average/NumEpisodes 120 +Average/StdReturn 6.93756 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68568 +GaussianMLPPolicy/KLAfter 0.00195872 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.88603e-05 +GaussianMLPPolicy/LossBefore -5.72205e-09 +GaussianMLPPolicy/dLoss 3.88546e-05 +Iteration 418 +MetaTest/Average/AverageDiscountedReturn -49.6256 +MetaTest/Average/AverageReturn -49.6256 +MetaTest/Average/Iteration 418 +MetaTest/Average/MaxReturn -39.5342 +MetaTest/Average/MinReturn -126.56 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 18.0275 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.6256 +MetaTest/__unnamed_task__/AverageReturn -49.6256 +MetaTest/__unnamed_task__/Iteration 418 +MetaTest/__unnamed_task__/MaxReturn -39.5342 +MetaTest/__unnamed_task__/MinReturn -126.56 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 18.0275 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0112e+07 +__unnamed_task__/AverageDiscountedReturn -26.0981 +__unnamed_task__/AverageReturn -49.8901 +__unnamed_task__/Iteration 418 +__unnamed_task__/MaxReturn -39.8408 +__unnamed_task__/MinReturn -72.5622 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.93756 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 04:44:40 | [maml_trainer] epoch #419 | Sampling for adapation and meta-testing... +2025-04-12 04:48:45 | [maml_trainer] epoch #419 | Finished meta-testing... +2025-04-12 04:48:45 | [maml_trainer] epoch #419 | Saving snapshot... +2025-04-12 04:49:08 | [maml_trainer] epoch #419 | Saved +2025-04-12 04:49:08 | [maml_trainer] epoch #419 | Time 734992.03 s +2025-04-12 04:49:08 | [maml_trainer] epoch #419 | EpochTime 1724.08 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.1537 +Average/AverageReturn -47.182 +Average/Iteration 419 +Average/MaxReturn -38.887 +Average/MinReturn -62.8229 +Average/NumEpisodes 120 +Average/StdReturn 4.41433 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68569 +GaussianMLPPolicy/KLAfter 0.00338315 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000109456 +GaussianMLPPolicy/LossBefore 1.98682e-09 +GaussianMLPPolicy/dLoss 0.000109457 +Iteration 419 +MetaTest/Average/AverageDiscountedReturn -47.4648 +MetaTest/Average/AverageReturn -47.4648 +MetaTest/Average/Iteration 419 +MetaTest/Average/MaxReturn -40.3317 +MetaTest/Average/MinReturn -66.7768 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.40842 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4648 +MetaTest/__unnamed_task__/AverageReturn -47.4648 +MetaTest/__unnamed_task__/Iteration 419 +MetaTest/__unnamed_task__/MaxReturn -40.3317 +MetaTest/__unnamed_task__/MinReturn -66.7768 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.40842 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.016e+07 +__unnamed_task__/AverageDiscountedReturn -25.1537 +__unnamed_task__/AverageReturn -47.182 +__unnamed_task__/Iteration 419 +__unnamed_task__/MaxReturn -38.887 +__unnamed_task__/MinReturn -62.8229 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.41433 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 05:13:29 | [maml_trainer] epoch #420 | Sampling for adapation and meta-testing... +2025-04-12 05:17:35 | [maml_trainer] epoch #420 | Finished meta-testing... +2025-04-12 05:17:35 | [maml_trainer] epoch #420 | Saving snapshot... +2025-04-12 05:17:57 | [maml_trainer] epoch #420 | Saved +2025-04-12 05:17:57 | [maml_trainer] epoch #420 | Time 736721.38 s +2025-04-12 05:17:57 | [maml_trainer] epoch #420 | EpochTime 1729.35 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.6389 +Average/AverageReturn -48.631 +Average/Iteration 420 +Average/MaxReturn -38.7306 +Average/MinReturn -67.574 +Average/NumEpisodes 120 +Average/StdReturn 6.04645 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6867 +GaussianMLPPolicy/KLAfter 0.00544083 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000136226 +GaussianMLPPolicy/LossBefore -9.53674e-10 +GaussianMLPPolicy/dLoss -0.000136227 +Iteration 420 +MetaTest/Average/AverageDiscountedReturn -48.6493 +MetaTest/Average/AverageReturn -48.6493 +MetaTest/Average/Iteration 420 +MetaTest/Average/MaxReturn -40.9392 +MetaTest/Average/MinReturn -58.7531 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.61899 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.6493 +MetaTest/__unnamed_task__/AverageReturn -48.6493 +MetaTest/__unnamed_task__/Iteration 420 +MetaTest/__unnamed_task__/MaxReturn -40.9392 +MetaTest/__unnamed_task__/MinReturn -58.7531 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.61899 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0208e+07 +__unnamed_task__/AverageDiscountedReturn -25.6389 +__unnamed_task__/AverageReturn -48.631 +__unnamed_task__/Iteration 420 +__unnamed_task__/MaxReturn -38.7306 +__unnamed_task__/MinReturn -67.574 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.04645 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 05:42:59 | [maml_trainer] epoch #421 | Sampling for adapation and meta-testing... +2025-04-12 05:47:02 | [maml_trainer] epoch #421 | Finished meta-testing... +2025-04-12 05:47:02 | [maml_trainer] epoch #421 | Saving snapshot... +2025-04-12 05:47:23 | [maml_trainer] epoch #421 | Saved +2025-04-12 05:47:23 | [maml_trainer] epoch #421 | Time 738487.31 s +2025-04-12 05:47:23 | [maml_trainer] epoch #421 | EpochTime 1765.93 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.238 +Average/AverageReturn -47.3541 +Average/Iteration 421 +Average/MaxReturn -37.7746 +Average/MinReturn -64.6536 +Average/NumEpisodes 120 +Average/StdReturn 5.06678 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68847 +GaussianMLPPolicy/KLAfter 0.00481901 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.73218e-05 +GaussianMLPPolicy/LossBefore -1.71661e-08 +GaussianMLPPolicy/dLoss 2.73046e-05 +Iteration 421 +MetaTest/Average/AverageDiscountedReturn -50.1252 +MetaTest/Average/AverageReturn -50.1252 +MetaTest/Average/Iteration 421 +MetaTest/Average/MaxReturn -41.2806 +MetaTest/Average/MinReturn -100.017 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.8504 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.1252 +MetaTest/__unnamed_task__/AverageReturn -50.1252 +MetaTest/__unnamed_task__/Iteration 421 +MetaTest/__unnamed_task__/MaxReturn -41.2806 +MetaTest/__unnamed_task__/MinReturn -100.017 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.8504 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0256e+07 +__unnamed_task__/AverageDiscountedReturn -25.238 +__unnamed_task__/AverageReturn -47.3541 +__unnamed_task__/Iteration 421 +__unnamed_task__/MaxReturn -37.7746 +__unnamed_task__/MinReturn -64.6536 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.06678 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 06:11:41 | [maml_trainer] epoch #422 | Sampling for adapation and meta-testing... +2025-04-12 06:15:47 | [maml_trainer] epoch #422 | Finished meta-testing... +2025-04-12 06:15:47 | [maml_trainer] epoch #422 | Saving snapshot... +2025-04-12 06:16:09 | [maml_trainer] epoch #422 | Saved +2025-04-12 06:16:09 | [maml_trainer] epoch #422 | Time 740213.87 s +2025-04-12 06:16:09 | [maml_trainer] epoch #422 | EpochTime 1726.56 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -25.0263 +Average/AverageReturn -46.8799 +Average/Iteration 422 +Average/MaxReturn -37.7596 +Average/MinReturn -69.4972 +Average/NumEpisodes 120 +Average/StdReturn 5.66455 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.691 +GaussianMLPPolicy/KLAfter 0.00674391 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.00022455 +GaussianMLPPolicy/LossBefore 3.33786e-09 +GaussianMLPPolicy/dLoss 0.000224553 +Iteration 422 +MetaTest/Average/AverageDiscountedReturn -47.2368 +MetaTest/Average/AverageReturn -47.2368 +MetaTest/Average/Iteration 422 +MetaTest/Average/MaxReturn -41.8377 +MetaTest/Average/MinReturn -60.1403 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.33291 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.2368 +MetaTest/__unnamed_task__/AverageReturn -47.2368 +MetaTest/__unnamed_task__/Iteration 422 +MetaTest/__unnamed_task__/MaxReturn -41.8377 +MetaTest/__unnamed_task__/MinReturn -60.1403 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.33291 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0304e+07 +__unnamed_task__/AverageDiscountedReturn -25.0263 +__unnamed_task__/AverageReturn -46.8799 +__unnamed_task__/Iteration 422 +__unnamed_task__/MaxReturn -37.7596 +__unnamed_task__/MinReturn -69.4972 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.66455 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 06:40:43 | [maml_trainer] epoch #423 | Sampling for adapation and meta-testing... +2025-04-12 06:44:46 | [maml_trainer] epoch #423 | Finished meta-testing... +2025-04-12 06:44:46 | [maml_trainer] epoch #423 | Saving snapshot... +2025-04-12 06:45:08 | [maml_trainer] epoch #423 | Saved +2025-04-12 06:45:08 | [maml_trainer] epoch #423 | Time 741952.43 s +2025-04-12 06:45:08 | [maml_trainer] epoch #423 | EpochTime 1738.55 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.0897 +Average/AverageReturn -47.2607 +Average/Iteration 423 +Average/MaxReturn -38.5597 +Average/MinReturn -126.469 +Average/NumEpisodes 120 +Average/StdReturn 8.73626 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69186 +GaussianMLPPolicy/KLAfter 0.00543504 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.07935e-05 +GaussianMLPPolicy/LossBefore 4.88758e-09 +GaussianMLPPolicy/dLoss 6.07984e-05 +Iteration 423 +MetaTest/Average/AverageDiscountedReturn -44.9376 +MetaTest/Average/AverageReturn -44.9376 +MetaTest/Average/Iteration 423 +MetaTest/Average/MaxReturn -41.3234 +MetaTest/Average/MinReturn -52.0088 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.92842 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.9376 +MetaTest/__unnamed_task__/AverageReturn -44.9376 +MetaTest/__unnamed_task__/Iteration 423 +MetaTest/__unnamed_task__/MaxReturn -41.3234 +MetaTest/__unnamed_task__/MinReturn -52.0088 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.92842 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0352e+07 +__unnamed_task__/AverageDiscountedReturn -25.0897 +__unnamed_task__/AverageReturn -47.2607 +__unnamed_task__/Iteration 423 +__unnamed_task__/MaxReturn -38.5597 +__unnamed_task__/MinReturn -126.469 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.73626 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 07:09:36 | [maml_trainer] epoch #424 | Sampling for adapation and meta-testing... +2025-04-12 07:13:41 | [maml_trainer] epoch #424 | Finished meta-testing... +2025-04-12 07:13:41 | [maml_trainer] epoch #424 | Saving snapshot... +2025-04-12 07:14:03 | [maml_trainer] epoch #424 | Saved +2025-04-12 07:14:03 | [maml_trainer] epoch #424 | Time 743687.27 s +2025-04-12 07:14:03 | [maml_trainer] epoch #424 | EpochTime 1734.84 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.0479 +Average/AverageReturn -47.4139 +Average/Iteration 424 +Average/MaxReturn -37.5423 +Average/MinReturn -123.548 +Average/NumEpisodes 120 +Average/StdReturn 9.71423 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69179 +GaussianMLPPolicy/KLAfter 0.00657709 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000108118 +GaussianMLPPolicy/LossBefore 2.90076e-09 +GaussianMLPPolicy/dLoss -0.000108115 +Iteration 424 +MetaTest/Average/AverageDiscountedReturn -45.1099 +MetaTest/Average/AverageReturn -45.1099 +MetaTest/Average/Iteration 424 +MetaTest/Average/MaxReturn -39.8151 +MetaTest/Average/MinReturn -51.5798 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.07353 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.1099 +MetaTest/__unnamed_task__/AverageReturn -45.1099 +MetaTest/__unnamed_task__/Iteration 424 +MetaTest/__unnamed_task__/MaxReturn -39.8151 +MetaTest/__unnamed_task__/MinReturn -51.5798 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.07353 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.04e+07 +__unnamed_task__/AverageDiscountedReturn -25.0479 +__unnamed_task__/AverageReturn -47.4139 +__unnamed_task__/Iteration 424 +__unnamed_task__/MaxReturn -37.5423 +__unnamed_task__/MinReturn -123.548 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.71423 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 07:38:35 | [maml_trainer] epoch #425 | Sampling for adapation and meta-testing... +2025-04-12 07:42:44 | [maml_trainer] epoch #425 | Finished meta-testing... +2025-04-12 07:42:44 | [maml_trainer] epoch #425 | Saving snapshot... +2025-04-12 07:43:05 | [maml_trainer] epoch #425 | Saved +2025-04-12 07:43:05 | [maml_trainer] epoch #425 | Time 745429.75 s +2025-04-12 07:43:05 | [maml_trainer] epoch #425 | EpochTime 1742.48 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.4655 +Average/AverageReturn -45.8498 +Average/Iteration 425 +Average/MaxReturn -37.3991 +Average/MinReturn -58.5289 +Average/NumEpisodes 120 +Average/StdReturn 4.33793 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69133 +GaussianMLPPolicy/KLAfter 0.00498156 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.36079e-06 +GaussianMLPPolicy/LossBefore -1.38283e-08 +GaussianMLPPolicy/dLoss 9.34696e-06 +Iteration 425 +MetaTest/Average/AverageDiscountedReturn -46.9447 +MetaTest/Average/AverageReturn -46.9447 +MetaTest/Average/Iteration 425 +MetaTest/Average/MaxReturn -41.267 +MetaTest/Average/MinReturn -64.7598 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.32906 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9447 +MetaTest/__unnamed_task__/AverageReturn -46.9447 +MetaTest/__unnamed_task__/Iteration 425 +MetaTest/__unnamed_task__/MaxReturn -41.267 +MetaTest/__unnamed_task__/MinReturn -64.7598 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.32906 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0448e+07 +__unnamed_task__/AverageDiscountedReturn -24.4655 +__unnamed_task__/AverageReturn -45.8498 +__unnamed_task__/Iteration 425 +__unnamed_task__/MaxReturn -37.3991 +__unnamed_task__/MinReturn -58.5289 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.33793 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 08:07:58 | [maml_trainer] epoch #426 | Sampling for adapation and meta-testing... +2025-04-12 08:12:05 | [maml_trainer] epoch #426 | Finished meta-testing... +2025-04-12 08:12:05 | [maml_trainer] epoch #426 | Saving snapshot... +2025-04-12 08:12:27 | [maml_trainer] epoch #426 | Saved +2025-04-12 08:12:27 | [maml_trainer] epoch #426 | Time 747191.03 s +2025-04-12 08:12:27 | [maml_trainer] epoch #426 | EpochTime 1761.27 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.9687 +Average/AverageReturn -47.263 +Average/Iteration 426 +Average/MaxReturn -38.6203 +Average/MinReturn -131.444 +Average/NumEpisodes 120 +Average/StdReturn 11.7702 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69132 +GaussianMLPPolicy/KLAfter 0.00274212 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.4908e-05 +GaussianMLPPolicy/LossBefore 9.17912e-09 +GaussianMLPPolicy/dLoss 6.49172e-05 +Iteration 426 +MetaTest/Average/AverageDiscountedReturn -46.0579 +MetaTest/Average/AverageReturn -46.0579 +MetaTest/Average/Iteration 426 +MetaTest/Average/MaxReturn -40.0957 +MetaTest/Average/MinReturn -52.8854 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.02208 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.0579 +MetaTest/__unnamed_task__/AverageReturn -46.0579 +MetaTest/__unnamed_task__/Iteration 426 +MetaTest/__unnamed_task__/MaxReturn -40.0957 +MetaTest/__unnamed_task__/MinReturn -52.8854 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.02208 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0496e+07 +__unnamed_task__/AverageDiscountedReturn -24.9687 +__unnamed_task__/AverageReturn -47.263 +__unnamed_task__/Iteration 426 +__unnamed_task__/MaxReturn -38.6203 +__unnamed_task__/MinReturn -131.444 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.7702 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 08:37:16 | [maml_trainer] epoch #427 | Sampling for adapation and meta-testing... +2025-04-12 08:41:21 | [maml_trainer] epoch #427 | Finished meta-testing... +2025-04-12 08:41:21 | [maml_trainer] epoch #427 | Saving snapshot... +2025-04-12 08:41:43 | [maml_trainer] epoch #427 | Saved +2025-04-12 08:41:43 | [maml_trainer] epoch #427 | Time 748947.10 s +2025-04-12 08:41:43 | [maml_trainer] epoch #427 | EpochTime 1756.06 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.7189 +Average/AverageReturn -46.7298 +Average/Iteration 427 +Average/MaxReturn -37.8251 +Average/MinReturn -131.031 +Average/NumEpisodes 120 +Average/StdReturn 9.57238 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69003 +GaussianMLPPolicy/KLAfter 0.00280768 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.68809e-05 +GaussianMLPPolicy/LossBefore 1.47025e-08 +GaussianMLPPolicy/dLoss -1.68662e-05 +Iteration 427 +MetaTest/Average/AverageDiscountedReturn -44.8657 +MetaTest/Average/AverageReturn -44.8657 +MetaTest/Average/Iteration 427 +MetaTest/Average/MaxReturn -37.5817 +MetaTest/Average/MinReturn -53.0405 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.9523 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.8657 +MetaTest/__unnamed_task__/AverageReturn -44.8657 +MetaTest/__unnamed_task__/Iteration 427 +MetaTest/__unnamed_task__/MaxReturn -37.5817 +MetaTest/__unnamed_task__/MinReturn -53.0405 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.9523 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0544e+07 +__unnamed_task__/AverageDiscountedReturn -24.7189 +__unnamed_task__/AverageReturn -46.7298 +__unnamed_task__/Iteration 427 +__unnamed_task__/MaxReturn -37.8251 +__unnamed_task__/MinReturn -131.031 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.57238 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 09:06:26 | [maml_trainer] epoch #428 | Sampling for adapation and meta-testing... +2025-04-12 09:10:33 | [maml_trainer] epoch #428 | Finished meta-testing... +2025-04-12 09:10:33 | [maml_trainer] epoch #428 | Saving snapshot... +2025-04-12 09:10:54 | [maml_trainer] epoch #428 | Saved +2025-04-12 09:10:54 | [maml_trainer] epoch #428 | Time 750698.57 s +2025-04-12 09:10:54 | [maml_trainer] epoch #428 | EpochTime 1751.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.4549 +Average/AverageReturn -45.6689 +Average/Iteration 428 +Average/MaxReturn -38.2038 +Average/MinReturn -57.1196 +Average/NumEpisodes 120 +Average/StdReturn 4.04191 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69019 +GaussianMLPPolicy/KLAfter 0.00416453 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000129856 +GaussianMLPPolicy/LossBefore -1.20004e-08 +GaussianMLPPolicy/dLoss 0.000129844 +Iteration 428 +MetaTest/Average/AverageDiscountedReturn -45.8633 +MetaTest/Average/AverageReturn -45.8633 +MetaTest/Average/Iteration 428 +MetaTest/Average/MaxReturn -39.7233 +MetaTest/Average/MinReturn -51.6863 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.76878 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8633 +MetaTest/__unnamed_task__/AverageReturn -45.8633 +MetaTest/__unnamed_task__/Iteration 428 +MetaTest/__unnamed_task__/MaxReturn -39.7233 +MetaTest/__unnamed_task__/MinReturn -51.6863 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.76878 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0592e+07 +__unnamed_task__/AverageDiscountedReturn -24.4549 +__unnamed_task__/AverageReturn -45.6689 +__unnamed_task__/Iteration 428 +__unnamed_task__/MaxReturn -38.2038 +__unnamed_task__/MinReturn -57.1196 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.04191 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 09:35:30 | [maml_trainer] epoch #429 | Sampling for adapation and meta-testing... +2025-04-12 09:39:35 | [maml_trainer] epoch #429 | Finished meta-testing... +2025-04-12 09:39:35 | [maml_trainer] epoch #429 | Saving snapshot... +2025-04-12 09:39:56 | [maml_trainer] epoch #429 | Saved +2025-04-12 09:39:56 | [maml_trainer] epoch #429 | Time 752440.53 s +2025-04-12 09:39:56 | [maml_trainer] epoch #429 | EpochTime 1741.95 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.4585 +Average/AverageReturn -45.6438 +Average/Iteration 429 +Average/MaxReturn -39.1163 +Average/MinReturn -61.9524 +Average/NumEpisodes 120 +Average/StdReturn 4.2234 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69115 +GaussianMLPPolicy/KLAfter 0.00683764 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000152164 +GaussianMLPPolicy/LossBefore -5.72205e-09 +GaussianMLPPolicy/dLoss 0.000152159 +Iteration 429 +MetaTest/Average/AverageDiscountedReturn -46.2572 +MetaTest/Average/AverageReturn -46.2572 +MetaTest/Average/Iteration 429 +MetaTest/Average/MaxReturn -39.7968 +MetaTest/Average/MinReturn -54.9442 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.72915 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.2572 +MetaTest/__unnamed_task__/AverageReturn -46.2572 +MetaTest/__unnamed_task__/Iteration 429 +MetaTest/__unnamed_task__/MaxReturn -39.7968 +MetaTest/__unnamed_task__/MinReturn -54.9442 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.72915 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.064e+07 +__unnamed_task__/AverageDiscountedReturn -24.4585 +__unnamed_task__/AverageReturn -45.6438 +__unnamed_task__/Iteration 429 +__unnamed_task__/MaxReturn -39.1163 +__unnamed_task__/MinReturn -61.9524 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.2234 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 10:04:38 | [maml_trainer] epoch #430 | Sampling for adapation and meta-testing... +2025-04-12 10:08:42 | [maml_trainer] epoch #430 | Finished meta-testing... +2025-04-12 10:08:42 | [maml_trainer] epoch #430 | Saving snapshot... +2025-04-12 10:09:05 | [maml_trainer] epoch #430 | Saved +2025-04-12 10:09:05 | [maml_trainer] epoch #430 | Time 754189.30 s +2025-04-12 10:09:05 | [maml_trainer] epoch #430 | EpochTime 1748.77 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.7478 +Average/AverageReturn -46.1474 +Average/Iteration 430 +Average/MaxReturn -37.3128 +Average/MinReturn -62.966 +Average/NumEpisodes 120 +Average/StdReturn 4.89072 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69109 +GaussianMLPPolicy/KLAfter 0.00604016 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000140621 +GaussianMLPPolicy/LossBefore 6.67572e-09 +GaussianMLPPolicy/dLoss -0.000140615 +Iteration 430 +MetaTest/Average/AverageDiscountedReturn -44.8423 +MetaTest/Average/AverageReturn -44.8423 +MetaTest/Average/Iteration 430 +MetaTest/Average/MaxReturn -41.5991 +MetaTest/Average/MinReturn -52.2215 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 2.43119 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.8423 +MetaTest/__unnamed_task__/AverageReturn -44.8423 +MetaTest/__unnamed_task__/Iteration 430 +MetaTest/__unnamed_task__/MaxReturn -41.5991 +MetaTest/__unnamed_task__/MinReturn -52.2215 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 2.43119 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0688e+07 +__unnamed_task__/AverageDiscountedReturn -24.7478 +__unnamed_task__/AverageReturn -46.1474 +__unnamed_task__/Iteration 430 +__unnamed_task__/MaxReturn -37.3128 +__unnamed_task__/MinReturn -62.966 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 4.89072 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 10:33:43 | [maml_trainer] epoch #431 | Sampling for adapation and meta-testing... +2025-04-12 10:37:52 | [maml_trainer] epoch #431 | Finished meta-testing... +2025-04-12 10:37:52 | [maml_trainer] epoch #431 | Saving snapshot... +2025-04-12 10:38:13 | [maml_trainer] epoch #431 | Saved +2025-04-12 10:38:13 | [maml_trainer] epoch #431 | Time 755937.76 s +2025-04-12 10:38:13 | [maml_trainer] epoch #431 | EpochTime 1748.46 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.454 +Average/AverageReturn -45.5316 +Average/Iteration 431 +Average/MaxReturn -38.0984 +Average/MinReturn -92.7389 +Average/NumEpisodes 120 +Average/StdReturn 6.35722 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68998 +GaussianMLPPolicy/KLAfter 0.00488215 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.25553e-05 +GaussianMLPPolicy/LossBefore 1.50999e-09 +GaussianMLPPolicy/dLoss -9.25538e-05 +Iteration 431 +MetaTest/Average/AverageDiscountedReturn -45.8107 +MetaTest/Average/AverageReturn -45.8107 +MetaTest/Average/Iteration 431 +MetaTest/Average/MaxReturn -41.1511 +MetaTest/Average/MinReturn -58.8066 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.0006 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8107 +MetaTest/__unnamed_task__/AverageReturn -45.8107 +MetaTest/__unnamed_task__/Iteration 431 +MetaTest/__unnamed_task__/MaxReturn -41.1511 +MetaTest/__unnamed_task__/MinReturn -58.8066 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.0006 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0736e+07 +__unnamed_task__/AverageDiscountedReturn -24.454 +__unnamed_task__/AverageReturn -45.5316 +__unnamed_task__/Iteration 431 +__unnamed_task__/MaxReturn -38.0984 +__unnamed_task__/MinReturn -92.7389 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.35722 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 11:02:48 | [maml_trainer] epoch #432 | Sampling for adapation and meta-testing... +2025-04-12 11:06:53 | [maml_trainer] epoch #432 | Finished meta-testing... +2025-04-12 11:06:53 | [maml_trainer] epoch #432 | Saving snapshot... +2025-04-12 11:07:15 | [maml_trainer] epoch #432 | Saved +2025-04-12 11:07:15 | [maml_trainer] epoch #432 | Time 757679.07 s +2025-04-12 11:07:15 | [maml_trainer] epoch #432 | EpochTime 1741.30 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.3941 +Average/AverageReturn -45.9368 +Average/Iteration 432 +Average/MaxReturn -37.78 +Average/MinReturn -127.024 +Average/NumEpisodes 120 +Average/StdReturn 10.953 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68907 +GaussianMLPPolicy/KLAfter 0.00488181 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.17769e-05 +GaussianMLPPolicy/LossBefore -3.73522e-09 +GaussianMLPPolicy/dLoss -8.17806e-05 +Iteration 432 +MetaTest/Average/AverageDiscountedReturn -45.3815 +MetaTest/Average/AverageReturn -45.3815 +MetaTest/Average/Iteration 432 +MetaTest/Average/MaxReturn -40.2913 +MetaTest/Average/MinReturn -61.9352 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.00687 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.3815 +MetaTest/__unnamed_task__/AverageReturn -45.3815 +MetaTest/__unnamed_task__/Iteration 432 +MetaTest/__unnamed_task__/MaxReturn -40.2913 +MetaTest/__unnamed_task__/MinReturn -61.9352 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.00687 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0784e+07 +__unnamed_task__/AverageDiscountedReturn -24.3941 +__unnamed_task__/AverageReturn -45.9368 +__unnamed_task__/Iteration 432 +__unnamed_task__/MaxReturn -37.78 +__unnamed_task__/MinReturn -127.024 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.953 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 11:31:42 | [maml_trainer] epoch #433 | Sampling for adapation and meta-testing... +2025-04-12 11:35:45 | [maml_trainer] epoch #433 | Finished meta-testing... +2025-04-12 11:35:45 | [maml_trainer] epoch #433 | Saving snapshot... +2025-04-12 11:36:07 | [maml_trainer] epoch #433 | Saved +2025-04-12 11:36:07 | [maml_trainer] epoch #433 | Time 759411.31 s +2025-04-12 11:36:07 | [maml_trainer] epoch #433 | EpochTime 1732.24 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.6132 +Average/AverageReturn -45.7982 +Average/Iteration 433 +Average/MaxReturn -37.5116 +Average/MinReturn -79.0186 +Average/NumEpisodes 120 +Average/StdReturn 5.58344 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68796 +GaussianMLPPolicy/KLAfter 0.00658139 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.75164e-06 +GaussianMLPPolicy/LossBefore 2.30471e-09 +GaussianMLPPolicy/dLoss -9.74933e-06 +Iteration 433 +MetaTest/Average/AverageDiscountedReturn -44.3107 +MetaTest/Average/AverageReturn -44.3107 +MetaTest/Average/Iteration 433 +MetaTest/Average/MaxReturn -39.1497 +MetaTest/Average/MinReturn -57.362 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.0113 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.3107 +MetaTest/__unnamed_task__/AverageReturn -44.3107 +MetaTest/__unnamed_task__/Iteration 433 +MetaTest/__unnamed_task__/MaxReturn -39.1497 +MetaTest/__unnamed_task__/MinReturn -57.362 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.0113 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0832e+07 +__unnamed_task__/AverageDiscountedReturn -24.6132 +__unnamed_task__/AverageReturn -45.7982 +__unnamed_task__/Iteration 433 +__unnamed_task__/MaxReturn -37.5116 +__unnamed_task__/MinReturn -79.0186 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.58344 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 12:00:46 | [maml_trainer] epoch #434 | Sampling for adapation and meta-testing... +2025-04-12 12:04:54 | [maml_trainer] epoch #434 | Finished meta-testing... +2025-04-12 12:04:54 | [maml_trainer] epoch #434 | Saving snapshot... +2025-04-12 12:05:16 | [maml_trainer] epoch #434 | Saved +2025-04-12 12:05:16 | [maml_trainer] epoch #434 | Time 761160.35 s +2025-04-12 12:05:16 | [maml_trainer] epoch #434 | EpochTime 1749.03 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.7793 +Average/AverageReturn -46.5032 +Average/Iteration 434 +Average/MaxReturn -38.2494 +Average/MinReturn -108.809 +Average/NumEpisodes 120 +Average/StdReturn 7.97819 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6871 +GaussianMLPPolicy/KLAfter 0.00558726 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000145513 +GaussianMLPPolicy/LossBefore 1.1603e-08 +GaussianMLPPolicy/dLoss -0.000145501 +Iteration 434 +MetaTest/Average/AverageDiscountedReturn -44.1156 +MetaTest/Average/AverageReturn -44.1156 +MetaTest/Average/Iteration 434 +MetaTest/Average/MaxReturn -37.618 +MetaTest/Average/MinReturn -50.7268 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.28776 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.1156 +MetaTest/__unnamed_task__/AverageReturn -44.1156 +MetaTest/__unnamed_task__/Iteration 434 +MetaTest/__unnamed_task__/MaxReturn -37.618 +MetaTest/__unnamed_task__/MinReturn -50.7268 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.28776 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.088e+07 +__unnamed_task__/AverageDiscountedReturn -24.7793 +__unnamed_task__/AverageReturn -46.5032 +__unnamed_task__/Iteration 434 +__unnamed_task__/MaxReturn -38.2494 +__unnamed_task__/MinReturn -108.809 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.97819 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 12:29:51 | [maml_trainer] epoch #435 | Sampling for adapation and meta-testing... +2025-04-12 12:33:53 | [maml_trainer] epoch #435 | Finished meta-testing... +2025-04-12 12:33:53 | [maml_trainer] epoch #435 | Saving snapshot... +2025-04-12 12:34:15 | [maml_trainer] epoch #435 | Saved +2025-04-12 12:34:15 | [maml_trainer] epoch #435 | Time 762899.33 s +2025-04-12 12:34:15 | [maml_trainer] epoch #435 | EpochTime 1738.98 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.4541 +Average/AverageReturn -46.0047 +Average/Iteration 435 +Average/MaxReturn -37.2202 +Average/MinReturn -135.432 +Average/NumEpisodes 120 +Average/StdReturn 10.0211 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68645 +GaussianMLPPolicy/KLAfter 0.00446326 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.30159e-05 +GaussianMLPPolicy/LossBefore 4.09285e-09 +GaussianMLPPolicy/dLoss -5.30118e-05 +Iteration 435 +MetaTest/Average/AverageDiscountedReturn -44.2343 +MetaTest/Average/AverageReturn -44.2343 +MetaTest/Average/Iteration 435 +MetaTest/Average/MaxReturn -35.8434 +MetaTest/Average/MinReturn -51.9248 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.44788 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.2343 +MetaTest/__unnamed_task__/AverageReturn -44.2343 +MetaTest/__unnamed_task__/Iteration 435 +MetaTest/__unnamed_task__/MaxReturn -35.8434 +MetaTest/__unnamed_task__/MinReturn -51.9248 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.44788 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0928e+07 +__unnamed_task__/AverageDiscountedReturn -24.4541 +__unnamed_task__/AverageReturn -46.0047 +__unnamed_task__/Iteration 435 +__unnamed_task__/MaxReturn -37.2202 +__unnamed_task__/MinReturn -135.432 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.0211 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 12:58:42 | [maml_trainer] epoch #436 | Sampling for adapation and meta-testing... +2025-04-12 13:02:53 | [maml_trainer] epoch #436 | Finished meta-testing... +2025-04-12 13:02:53 | [maml_trainer] epoch #436 | Saving snapshot... +2025-04-12 13:03:16 | [maml_trainer] epoch #436 | Saved +2025-04-12 13:03:16 | [maml_trainer] epoch #436 | Time 764640.05 s +2025-04-12 13:03:16 | [maml_trainer] epoch #436 | EpochTime 1740.72 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.0031 +Average/AverageReturn -44.9791 +Average/Iteration 436 +Average/MaxReturn -37.6222 +Average/MinReturn -96.2741 +Average/NumEpisodes 120 +Average/StdReturn 7.66114 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68526 +GaussianMLPPolicy/KLAfter 0.00451956 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.48788e-05 +GaussianMLPPolicy/LossBefore 1.04109e-08 +GaussianMLPPolicy/dLoss -9.48684e-05 +Iteration 436 +MetaTest/Average/AverageDiscountedReturn -47.0124 +MetaTest/Average/AverageReturn -47.0124 +MetaTest/Average/Iteration 436 +MetaTest/Average/MaxReturn -37.795 +MetaTest/Average/MinReturn -61.6111 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.96871 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.0124 +MetaTest/__unnamed_task__/AverageReturn -47.0124 +MetaTest/__unnamed_task__/Iteration 436 +MetaTest/__unnamed_task__/MaxReturn -37.795 +MetaTest/__unnamed_task__/MinReturn -61.6111 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.96871 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.0976e+07 +__unnamed_task__/AverageDiscountedReturn -24.0031 +__unnamed_task__/AverageReturn -44.9791 +__unnamed_task__/Iteration 436 +__unnamed_task__/MaxReturn -37.6222 +__unnamed_task__/MinReturn -96.2741 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.66114 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 13:27:48 | [maml_trainer] epoch #437 | Sampling for adapation and meta-testing... +2025-04-12 13:31:57 | [maml_trainer] epoch #437 | Finished meta-testing... +2025-04-12 13:31:57 | [maml_trainer] epoch #437 | Saving snapshot... +2025-04-12 13:32:18 | [maml_trainer] epoch #437 | Saved +2025-04-12 13:32:18 | [maml_trainer] epoch #437 | Time 766382.60 s +2025-04-12 13:32:18 | [maml_trainer] epoch #437 | EpochTime 1742.55 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.6174 +Average/AverageReturn -46.135 +Average/Iteration 437 +Average/MaxReturn -37.2563 +Average/MinReturn -116.1 +Average/NumEpisodes 120 +Average/StdReturn 8.22173 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68333 +GaussianMLPPolicy/KLAfter 0.00580051 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000100231 +GaussianMLPPolicy/LossBefore 8.54333e-09 +GaussianMLPPolicy/dLoss 0.00010024 +Iteration 437 +MetaTest/Average/AverageDiscountedReturn -46.2404 +MetaTest/Average/AverageReturn -46.2404 +MetaTest/Average/Iteration 437 +MetaTest/Average/MaxReturn -39.76 +MetaTest/Average/MinReturn -71.7823 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.66027 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.2404 +MetaTest/__unnamed_task__/AverageReturn -46.2404 +MetaTest/__unnamed_task__/Iteration 437 +MetaTest/__unnamed_task__/MaxReturn -39.76 +MetaTest/__unnamed_task__/MinReturn -71.7823 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.66027 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1024e+07 +__unnamed_task__/AverageDiscountedReturn -24.6174 +__unnamed_task__/AverageReturn -46.135 +__unnamed_task__/Iteration 437 +__unnamed_task__/MaxReturn -37.2563 +__unnamed_task__/MinReturn -116.1 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.22173 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 13:56:46 | [maml_trainer] epoch #438 | Sampling for adapation and meta-testing... +2025-04-12 14:00:51 | [maml_trainer] epoch #438 | Finished meta-testing... +2025-04-12 14:00:51 | [maml_trainer] epoch #438 | Saving snapshot... +2025-04-12 14:01:13 | [maml_trainer] epoch #438 | Saved +2025-04-12 14:01:13 | [maml_trainer] epoch #438 | Time 768117.44 s +2025-04-12 14:01:13 | [maml_trainer] epoch #438 | EpochTime 1734.83 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.6307 +Average/AverageReturn -46.0917 +Average/Iteration 438 +Average/MaxReturn -37.1681 +Average/MinReturn -62.0213 +Average/NumEpisodes 120 +Average/StdReturn 5.15375 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68198 +GaussianMLPPolicy/KLAfter 0.00608549 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.05978e-05 +GaussianMLPPolicy/LossBefore -6.35783e-10 +GaussianMLPPolicy/dLoss 7.05972e-05 +Iteration 438 +MetaTest/Average/AverageDiscountedReturn -49.5184 +MetaTest/Average/AverageReturn -49.5184 +MetaTest/Average/Iteration 438 +MetaTest/Average/MaxReturn -37.8345 +MetaTest/Average/MinReturn -84.958 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 10.7737 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.5184 +MetaTest/__unnamed_task__/AverageReturn -49.5184 +MetaTest/__unnamed_task__/Iteration 438 +MetaTest/__unnamed_task__/MaxReturn -37.8345 +MetaTest/__unnamed_task__/MinReturn -84.958 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 10.7737 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1072e+07 +__unnamed_task__/AverageDiscountedReturn -24.6307 +__unnamed_task__/AverageReturn -46.0917 +__unnamed_task__/Iteration 438 +__unnamed_task__/MaxReturn -37.1681 +__unnamed_task__/MinReturn -62.0213 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 5.15375 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 14:25:30 | [maml_trainer] epoch #439 | Sampling for adapation and meta-testing... +2025-04-12 14:29:34 | [maml_trainer] epoch #439 | Finished meta-testing... +2025-04-12 14:29:34 | [maml_trainer] epoch #439 | Saving snapshot... +2025-04-12 14:29:57 | [maml_trainer] epoch #439 | Saved +2025-04-12 14:29:57 | [maml_trainer] epoch #439 | Time 769841.13 s +2025-04-12 14:29:57 | [maml_trainer] epoch #439 | EpochTime 1723.69 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.4009 +Average/AverageReturn -45.8002 +Average/Iteration 439 +Average/MaxReturn -36.2447 +Average/MinReturn -107.566 +Average/NumEpisodes 120 +Average/StdReturn 7.5982 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68153 +GaussianMLPPolicy/KLAfter 0.00526735 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.18266e-05 +GaussianMLPPolicy/LossBefore 5.64257e-09 +GaussianMLPPolicy/dLoss 8.18322e-05 +Iteration 439 +MetaTest/Average/AverageDiscountedReturn -45.9622 +MetaTest/Average/AverageReturn -45.9622 +MetaTest/Average/Iteration 439 +MetaTest/Average/MaxReturn -39.2487 +MetaTest/Average/MinReturn -74.2821 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.339 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.9622 +MetaTest/__unnamed_task__/AverageReturn -45.9622 +MetaTest/__unnamed_task__/Iteration 439 +MetaTest/__unnamed_task__/MaxReturn -39.2487 +MetaTest/__unnamed_task__/MinReturn -74.2821 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.339 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.112e+07 +__unnamed_task__/AverageDiscountedReturn -24.4009 +__unnamed_task__/AverageReturn -45.8002 +__unnamed_task__/Iteration 439 +__unnamed_task__/MaxReturn -36.2447 +__unnamed_task__/MinReturn -107.566 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.5982 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 14:54:32 | [maml_trainer] epoch #440 | Sampling for adapation and meta-testing... +2025-04-12 14:58:36 | [maml_trainer] epoch #440 | Finished meta-testing... +2025-04-12 14:58:36 | [maml_trainer] epoch #440 | Saving snapshot... +2025-04-12 14:58:57 | [maml_trainer] epoch #440 | Saved +2025-04-12 14:58:57 | [maml_trainer] epoch #440 | Time 771581.26 s +2025-04-12 14:58:57 | [maml_trainer] epoch #440 | EpochTime 1740.13 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.7787 +Average/AverageReturn -46.4537 +Average/Iteration 440 +Average/MaxReturn -38.2624 +Average/MinReturn -97.6427 +Average/NumEpisodes 120 +Average/StdReturn 7.84305 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68215 +GaussianMLPPolicy/KLAfter 0.00442547 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000167479 +GaussianMLPPolicy/LossBefore -3.09944e-09 +GaussianMLPPolicy/dLoss 0.000167476 +Iteration 440 +MetaTest/Average/AverageDiscountedReturn -44.9835 +MetaTest/Average/AverageReturn -44.9835 +MetaTest/Average/Iteration 440 +MetaTest/Average/MaxReturn -37.6165 +MetaTest/Average/MinReturn -58.3052 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.19881 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.9835 +MetaTest/__unnamed_task__/AverageReturn -44.9835 +MetaTest/__unnamed_task__/Iteration 440 +MetaTest/__unnamed_task__/MaxReturn -37.6165 +MetaTest/__unnamed_task__/MinReturn -58.3052 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.19881 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1168e+07 +__unnamed_task__/AverageDiscountedReturn -24.7787 +__unnamed_task__/AverageReturn -46.4537 +__unnamed_task__/Iteration 440 +__unnamed_task__/MaxReturn -38.2624 +__unnamed_task__/MinReturn -97.6427 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.84305 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 15:23:11 | [maml_trainer] epoch #441 | Sampling for adapation and meta-testing... +2025-04-12 15:27:12 | [maml_trainer] epoch #441 | Finished meta-testing... +2025-04-12 15:27:12 | [maml_trainer] epoch #441 | Saving snapshot... +2025-04-12 15:27:34 | [maml_trainer] epoch #441 | Saved +2025-04-12 15:27:34 | [maml_trainer] epoch #441 | Time 773298.68 s +2025-04-12 15:27:34 | [maml_trainer] epoch #441 | EpochTime 1717.42 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.7786 +Average/AverageReturn -47.0021 +Average/Iteration 441 +Average/MaxReturn -37.2986 +Average/MinReturn -127 +Average/NumEpisodes 120 +Average/StdReturn 11.1218 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6831 +GaussianMLPPolicy/KLAfter 0.00431396 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.0596e-05 +GaussianMLPPolicy/LossBefore -3.53654e-09 +GaussianMLPPolicy/dLoss 9.05924e-05 +Iteration 441 +MetaTest/Average/AverageDiscountedReturn -48.2443 +MetaTest/Average/AverageReturn -48.2443 +MetaTest/Average/Iteration 441 +MetaTest/Average/MaxReturn -39.3287 +MetaTest/Average/MinReturn -120.578 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.7803 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.2443 +MetaTest/__unnamed_task__/AverageReturn -48.2443 +MetaTest/__unnamed_task__/Iteration 441 +MetaTest/__unnamed_task__/MaxReturn -39.3287 +MetaTest/__unnamed_task__/MinReturn -120.578 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.7803 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1216e+07 +__unnamed_task__/AverageDiscountedReturn -24.7786 +__unnamed_task__/AverageReturn -47.0021 +__unnamed_task__/Iteration 441 +__unnamed_task__/MaxReturn -37.2986 +__unnamed_task__/MinReturn -127 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.1218 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 15:52:03 | [maml_trainer] epoch #442 | Sampling for adapation and meta-testing... +2025-04-12 15:56:08 | [maml_trainer] epoch #442 | Finished meta-testing... +2025-04-12 15:56:08 | [maml_trainer] epoch #442 | Saving snapshot... +2025-04-12 15:56:31 | [maml_trainer] epoch #442 | Saved +2025-04-12 15:56:31 | [maml_trainer] epoch #442 | Time 775035.04 s +2025-04-12 15:56:31 | [maml_trainer] epoch #442 | EpochTime 1736.36 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.7486 +Average/AverageReturn -46.8192 +Average/Iteration 442 +Average/MaxReturn -36.5909 +Average/MinReturn -84.7391 +Average/NumEpisodes 120 +Average/StdReturn 6.89742 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68385 +GaussianMLPPolicy/KLAfter 0.00438567 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000100238 +GaussianMLPPolicy/LossBefore 5.88099e-09 +GaussianMLPPolicy/dLoss -0.000100232 +Iteration 442 +MetaTest/Average/AverageDiscountedReturn -44.7947 +MetaTest/Average/AverageReturn -44.7947 +MetaTest/Average/Iteration 442 +MetaTest/Average/MaxReturn -38.4958 +MetaTest/Average/MinReturn -55.5427 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.30812 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.7947 +MetaTest/__unnamed_task__/AverageReturn -44.7947 +MetaTest/__unnamed_task__/Iteration 442 +MetaTest/__unnamed_task__/MaxReturn -38.4958 +MetaTest/__unnamed_task__/MinReturn -55.5427 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.30812 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1264e+07 +__unnamed_task__/AverageDiscountedReturn -24.7486 +__unnamed_task__/AverageReturn -46.8192 +__unnamed_task__/Iteration 442 +__unnamed_task__/MaxReturn -36.5909 +__unnamed_task__/MinReturn -84.7391 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.89742 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-12 16:20:58 | [maml_trainer] epoch #443 | Sampling for adapation and meta-testing... +2025-04-12 16:25:06 | [maml_trainer] epoch #443 | Finished meta-testing... +2025-04-12 16:25:06 | [maml_trainer] epoch #443 | Saving snapshot... +2025-04-12 16:25:27 | [maml_trainer] epoch #443 | Saved +2025-04-12 16:25:27 | [maml_trainer] epoch #443 | Time 776771.15 s +2025-04-12 16:25:27 | [maml_trainer] epoch #443 | EpochTime 1736.11 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.5915 +Average/AverageReturn -46.3637 +Average/Iteration 443 +Average/MaxReturn -37.0321 +Average/MinReturn -102.835 +Average/NumEpisodes 120 +Average/StdReturn 8.17182 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68529 +GaussianMLPPolicy/KLAfter 0.00234534 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.86147e-05 +GaussianMLPPolicy/LossBefore 1.23183e-09 +GaussianMLPPolicy/dLoss -1.86135e-05 +Iteration 443 +MetaTest/Average/AverageDiscountedReturn -46.9666 +MetaTest/Average/AverageReturn -46.9666 +MetaTest/Average/Iteration 443 +MetaTest/Average/MaxReturn -35.8224 +MetaTest/Average/MinReturn -64.6975 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.33295 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.9666 +MetaTest/__unnamed_task__/AverageReturn -46.9666 +MetaTest/__unnamed_task__/Iteration 443 +MetaTest/__unnamed_task__/MaxReturn -35.8224 +MetaTest/__unnamed_task__/MinReturn -64.6975 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.33295 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1312e+07 +__unnamed_task__/AverageDiscountedReturn -24.5915 +__unnamed_task__/AverageReturn -46.3637 +__unnamed_task__/Iteration 443 +__unnamed_task__/MaxReturn -37.0321 +__unnamed_task__/MinReturn -102.835 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.17182 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 16:50:01 | [maml_trainer] epoch #444 | Sampling for adapation and meta-testing... +2025-04-12 16:54:03 | [maml_trainer] epoch #444 | Finished meta-testing... +2025-04-12 16:54:03 | [maml_trainer] epoch #444 | Saving snapshot... +2025-04-12 16:54:24 | [maml_trainer] epoch #444 | Saved +2025-04-12 16:54:24 | [maml_trainer] epoch #444 | Time 778508.59 s +2025-04-12 16:54:24 | [maml_trainer] epoch #444 | EpochTime 1737.43 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.9099 +Average/AverageReturn -48.0851 +Average/Iteration 444 +Average/MaxReturn -37.0657 +Average/MinReturn -124.184 +Average/NumEpisodes 120 +Average/StdReturn 13.0359 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68601 +GaussianMLPPolicy/KLAfter 0.00290786 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.10431e-05 +GaussianMLPPolicy/LossBefore 1.02917e-08 +GaussianMLPPolicy/dLoss -7.10328e-05 +Iteration 444 +MetaTest/Average/AverageDiscountedReturn -49.2988 +MetaTest/Average/AverageReturn -49.2988 +MetaTest/Average/Iteration 444 +MetaTest/Average/MaxReturn -38.0731 +MetaTest/Average/MinReturn -95.5123 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.6878 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2988 +MetaTest/__unnamed_task__/AverageReturn -49.2988 +MetaTest/__unnamed_task__/Iteration 444 +MetaTest/__unnamed_task__/MaxReturn -38.0731 +MetaTest/__unnamed_task__/MinReturn -95.5123 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.6878 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.136e+07 +__unnamed_task__/AverageDiscountedReturn -24.9099 +__unnamed_task__/AverageReturn -48.0851 +__unnamed_task__/Iteration 444 +__unnamed_task__/MaxReturn -37.0657 +__unnamed_task__/MinReturn -124.184 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.0359 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 17:18:45 | [maml_trainer] epoch #445 | Sampling for adapation and meta-testing... +2025-04-12 17:22:50 | [maml_trainer] epoch #445 | Finished meta-testing... +2025-04-12 17:22:50 | [maml_trainer] epoch #445 | Saving snapshot... +2025-04-12 17:23:11 | [maml_trainer] epoch #445 | Saved +2025-04-12 17:23:11 | [maml_trainer] epoch #445 | Time 780235.89 s +2025-04-12 17:23:11 | [maml_trainer] epoch #445 | EpochTime 1727.30 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.5741 +Average/AverageReturn -47.3555 +Average/Iteration 445 +Average/MaxReturn -37.7101 +Average/MinReturn -134.612 +Average/NumEpisodes 120 +Average/StdReturn 12.1213 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68625 +GaussianMLPPolicy/KLAfter 0.00236335 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.05673e-05 +GaussianMLPPolicy/LossBefore -1.4027e-08 +GaussianMLPPolicy/dLoss -2.05813e-05 +Iteration 445 +MetaTest/Average/AverageDiscountedReturn -43.7294 +MetaTest/Average/AverageReturn -43.7294 +MetaTest/Average/Iteration 445 +MetaTest/Average/MaxReturn -36.7827 +MetaTest/Average/MinReturn -52.7779 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.42264 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -43.7294 +MetaTest/__unnamed_task__/AverageReturn -43.7294 +MetaTest/__unnamed_task__/Iteration 445 +MetaTest/__unnamed_task__/MaxReturn -36.7827 +MetaTest/__unnamed_task__/MinReturn -52.7779 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.42264 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1408e+07 +__unnamed_task__/AverageDiscountedReturn -24.5741 +__unnamed_task__/AverageReturn -47.3555 +__unnamed_task__/Iteration 445 +__unnamed_task__/MaxReturn -37.7101 +__unnamed_task__/MinReturn -134.612 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.1213 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 17:48:01 | [maml_trainer] epoch #446 | Sampling for adapation and meta-testing... +2025-04-12 17:52:10 | [maml_trainer] epoch #446 | Finished meta-testing... +2025-04-12 17:52:10 | [maml_trainer] epoch #446 | Saving snapshot... +2025-04-12 17:52:32 | [maml_trainer] epoch #446 | Saved +2025-04-12 17:52:32 | [maml_trainer] epoch #446 | Time 781996.70 s +2025-04-12 17:52:32 | [maml_trainer] epoch #446 | EpochTime 1760.81 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.5849 +Average/AverageReturn -46.8943 +Average/Iteration 446 +Average/MaxReturn -36.7121 +Average/MinReturn -100.575 +Average/NumEpisodes 120 +Average/StdReturn 10.3281 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68614 +GaussianMLPPolicy/KLAfter 0.00233374 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.18727e-05 +GaussianMLPPolicy/LossBefore -9.25859e-09 +GaussianMLPPolicy/dLoss 5.18635e-05 +Iteration 446 +MetaTest/Average/AverageDiscountedReturn -49.0933 +MetaTest/Average/AverageReturn -49.0933 +MetaTest/Average/Iteration 446 +MetaTest/Average/MaxReturn -37.3831 +MetaTest/Average/MinReturn -101.956 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.4867 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.0933 +MetaTest/__unnamed_task__/AverageReturn -49.0933 +MetaTest/__unnamed_task__/Iteration 446 +MetaTest/__unnamed_task__/MaxReturn -37.3831 +MetaTest/__unnamed_task__/MinReturn -101.956 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.4867 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1456e+07 +__unnamed_task__/AverageDiscountedReturn -24.5849 +__unnamed_task__/AverageReturn -46.8943 +__unnamed_task__/Iteration 446 +__unnamed_task__/MaxReturn -36.7121 +__unnamed_task__/MinReturn -100.575 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.3281 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 18:17:09 | [maml_trainer] epoch #447 | Sampling for adapation and meta-testing... +2025-04-12 18:21:10 | [maml_trainer] epoch #447 | Finished meta-testing... +2025-04-12 18:21:10 | [maml_trainer] epoch #447 | Saving snapshot... +2025-04-12 18:21:32 | [maml_trainer] epoch #447 | Saved +2025-04-12 18:21:32 | [maml_trainer] epoch #447 | Time 783736.72 s +2025-04-12 18:21:32 | [maml_trainer] epoch #447 | EpochTime 1740.01 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1287 +Average/AverageReturn -48.6332 +Average/Iteration 447 +Average/MaxReturn -36.9279 +Average/MinReturn -137.801 +Average/NumEpisodes 120 +Average/StdReturn 12.4693 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68738 +GaussianMLPPolicy/KLAfter 0.00242976 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 5.39103e-05 +GaussianMLPPolicy/LossBefore 7.11282e-09 +GaussianMLPPolicy/dLoss -5.39032e-05 +Iteration 447 +MetaTest/Average/AverageDiscountedReturn -44.7703 +MetaTest/Average/AverageReturn -44.7703 +MetaTest/Average/Iteration 447 +MetaTest/Average/MaxReturn -38.13 +MetaTest/Average/MinReturn -64.0873 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.16116 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -44.7703 +MetaTest/__unnamed_task__/AverageReturn -44.7703 +MetaTest/__unnamed_task__/Iteration 447 +MetaTest/__unnamed_task__/MaxReturn -38.13 +MetaTest/__unnamed_task__/MinReturn -64.0873 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.16116 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1504e+07 +__unnamed_task__/AverageDiscountedReturn -25.1287 +__unnamed_task__/AverageReturn -48.6332 +__unnamed_task__/Iteration 447 +__unnamed_task__/MaxReturn -36.9279 +__unnamed_task__/MinReturn -137.801 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.4693 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 19:02:51 | [maml_trainer] epoch #448 | Sampling for adapation and meta-testing... +2025-04-12 19:10:11 | [maml_trainer] epoch #448 | Finished meta-testing... +2025-04-12 19:10:11 | [maml_trainer] epoch #448 | Saving snapshot... +2025-04-12 19:10:51 | [maml_trainer] epoch #448 | Saved +2025-04-12 19:10:51 | [maml_trainer] epoch #448 | Time 786695.16 s +2025-04-12 19:10:51 | [maml_trainer] epoch #448 | EpochTime 2958.44 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1598 +Average/AverageReturn -49.3257 +Average/Iteration 448 +Average/MaxReturn -36.3882 +Average/MinReturn -133.012 +Average/NumEpisodes 120 +Average/StdReturn 16.1929 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68863 +GaussianMLPPolicy/KLAfter 0.000890228 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.46678e-05 +GaussianMLPPolicy/LossBefore 9.29832e-09 +GaussianMLPPolicy/dLoss -3.46585e-05 +Iteration 448 +MetaTest/Average/AverageDiscountedReturn -46.3732 +MetaTest/Average/AverageReturn -46.3732 +MetaTest/Average/Iteration 448 +MetaTest/Average/MaxReturn -37.8904 +MetaTest/Average/MinReturn -66.0798 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.74797 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.3732 +MetaTest/__unnamed_task__/AverageReturn -46.3732 +MetaTest/__unnamed_task__/Iteration 448 +MetaTest/__unnamed_task__/MaxReturn -37.8904 +MetaTest/__unnamed_task__/MinReturn -66.0798 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.74797 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1552e+07 +__unnamed_task__/AverageDiscountedReturn -25.1598 +__unnamed_task__/AverageReturn -49.3257 +__unnamed_task__/Iteration 448 +__unnamed_task__/MaxReturn -36.3882 +__unnamed_task__/MinReturn -133.012 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.1929 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 19:53:47 | [maml_trainer] epoch #449 | Sampling for adapation and meta-testing... +2025-04-12 20:00:55 | [maml_trainer] epoch #449 | Finished meta-testing... +2025-04-12 20:00:55 | [maml_trainer] epoch #449 | Saving snapshot... +2025-04-12 20:01:37 | [maml_trainer] epoch #449 | Saved +2025-04-12 20:01:37 | [maml_trainer] epoch #449 | Time 789741.06 s +2025-04-12 20:01:37 | [maml_trainer] epoch #449 | EpochTime 3045.90 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.2637 +Average/AverageReturn -49.3167 +Average/Iteration 449 +Average/MaxReturn -36.6811 +Average/MinReturn -133.926 +Average/NumEpisodes 120 +Average/StdReturn 15.2297 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68943 +GaussianMLPPolicy/KLAfter 0.0011468 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.04399e-05 +GaussianMLPPolicy/LossBefore 6.67572e-09 +GaussianMLPPolicy/dLoss 2.04465e-05 +Iteration 449 +MetaTest/Average/AverageDiscountedReturn -47.0777 +MetaTest/Average/AverageReturn -47.0777 +MetaTest/Average/Iteration 449 +MetaTest/Average/MaxReturn -36.1739 +MetaTest/Average/MinReturn -77.5793 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.56879 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.0777 +MetaTest/__unnamed_task__/AverageReturn -47.0777 +MetaTest/__unnamed_task__/Iteration 449 +MetaTest/__unnamed_task__/MaxReturn -36.1739 +MetaTest/__unnamed_task__/MinReturn -77.5793 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.56879 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.16e+07 +__unnamed_task__/AverageDiscountedReturn -25.2637 +__unnamed_task__/AverageReturn -49.3167 +__unnamed_task__/Iteration 449 +__unnamed_task__/MaxReturn -36.6811 +__unnamed_task__/MinReturn -133.926 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 15.2297 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 20:44:53 | [maml_trainer] epoch #450 | Sampling for adapation and meta-testing... +2025-04-12 20:50:36 | [maml_trainer] epoch #450 | Finished meta-testing... +2025-04-12 20:50:36 | [maml_trainer] epoch #450 | Saving snapshot... +2025-04-12 20:51:06 | [maml_trainer] epoch #450 | Saved +2025-04-12 20:51:06 | [maml_trainer] epoch #450 | Time 792710.51 s +2025-04-12 20:51:06 | [maml_trainer] epoch #450 | EpochTime 2969.45 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.6276 +Average/AverageReturn -46.9041 +Average/Iteration 450 +Average/MaxReturn -35.8054 +Average/MinReturn -128.904 +Average/NumEpisodes 120 +Average/StdReturn 10.8044 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69068 +GaussianMLPPolicy/KLAfter 0.00103666 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.56891e-05 +GaussianMLPPolicy/LossBefore 1.15236e-08 +GaussianMLPPolicy/dLoss 1.57006e-05 +Iteration 450 +MetaTest/Average/AverageDiscountedReturn -51.8638 +MetaTest/Average/AverageReturn -51.8638 +MetaTest/Average/Iteration 450 +MetaTest/Average/MaxReturn -37.3028 +MetaTest/Average/MinReturn -106.362 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.9365 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8638 +MetaTest/__unnamed_task__/AverageReturn -51.8638 +MetaTest/__unnamed_task__/Iteration 450 +MetaTest/__unnamed_task__/MaxReturn -37.3028 +MetaTest/__unnamed_task__/MinReturn -106.362 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.9365 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1648e+07 +__unnamed_task__/AverageDiscountedReturn -24.6276 +__unnamed_task__/AverageReturn -46.9041 +__unnamed_task__/Iteration 450 +__unnamed_task__/MaxReturn -35.8054 +__unnamed_task__/MinReturn -128.904 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.8044 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 21:19:19 | [maml_trainer] epoch #451 | Sampling for adapation and meta-testing... +2025-04-12 21:23:25 | [maml_trainer] epoch #451 | Finished meta-testing... +2025-04-12 21:23:25 | [maml_trainer] epoch #451 | Saving snapshot... +2025-04-12 21:23:46 | [maml_trainer] epoch #451 | Saved +2025-04-12 21:23:46 | [maml_trainer] epoch #451 | Time 794670.31 s +2025-04-12 21:23:46 | [maml_trainer] epoch #451 | EpochTime 1959.80 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.0583 +Average/AverageReturn -47.963 +Average/Iteration 451 +Average/MaxReturn -37.3314 +Average/MinReturn -102.18 +Average/NumEpisodes 120 +Average/StdReturn 9.21532 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69133 +GaussianMLPPolicy/KLAfter 0.00174953 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.86406e-05 +GaussianMLPPolicy/LossBefore 7.15256e-09 +GaussianMLPPolicy/dLoss -2.86334e-05 +Iteration 451 +MetaTest/Average/AverageDiscountedReturn -47.119 +MetaTest/Average/AverageReturn -47.119 +MetaTest/Average/Iteration 451 +MetaTest/Average/MaxReturn -37.1325 +MetaTest/Average/MinReturn -99.7285 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.1148 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.119 +MetaTest/__unnamed_task__/AverageReturn -47.119 +MetaTest/__unnamed_task__/Iteration 451 +MetaTest/__unnamed_task__/MaxReturn -37.1325 +MetaTest/__unnamed_task__/MinReturn -99.7285 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.1148 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1696e+07 +__unnamed_task__/AverageDiscountedReturn -25.0583 +__unnamed_task__/AverageReturn -47.963 +__unnamed_task__/Iteration 451 +__unnamed_task__/MaxReturn -37.3314 +__unnamed_task__/MinReturn -102.18 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.21532 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 21:48:19 | [maml_trainer] epoch #452 | Sampling for adapation and meta-testing... +2025-04-12 21:52:24 | [maml_trainer] epoch #452 | Finished meta-testing... +2025-04-12 21:52:24 | [maml_trainer] epoch #452 | Saving snapshot... +2025-04-12 21:52:45 | [maml_trainer] epoch #452 | Saved +2025-04-12 21:52:45 | [maml_trainer] epoch #452 | Time 796409.69 s +2025-04-12 21:52:45 | [maml_trainer] epoch #452 | EpochTime 1739.38 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.7938 +Average/AverageReturn -47.7124 +Average/Iteration 452 +Average/MaxReturn -36.6009 +Average/MinReturn -118.882 +Average/NumEpisodes 120 +Average/StdReturn 12.0522 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69207 +GaussianMLPPolicy/KLAfter 0.0024542 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.29246e-05 +GaussianMLPPolicy/LossBefore 1.22388e-08 +GaussianMLPPolicy/dLoss 4.29368e-05 +Iteration 452 +MetaTest/Average/AverageDiscountedReturn -48.1207 +MetaTest/Average/AverageReturn -48.1207 +MetaTest/Average/Iteration 452 +MetaTest/Average/MaxReturn -38.2305 +MetaTest/Average/MinReturn -72.3435 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.75997 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1207 +MetaTest/__unnamed_task__/AverageReturn -48.1207 +MetaTest/__unnamed_task__/Iteration 452 +MetaTest/__unnamed_task__/MaxReturn -38.2305 +MetaTest/__unnamed_task__/MinReturn -72.3435 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.75997 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1744e+07 +__unnamed_task__/AverageDiscountedReturn -24.7938 +__unnamed_task__/AverageReturn -47.7124 +__unnamed_task__/Iteration 452 +__unnamed_task__/MaxReturn -36.6009 +__unnamed_task__/MinReturn -118.882 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.0522 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 22:17:22 | [maml_trainer] epoch #453 | Sampling for adapation and meta-testing... +2025-04-12 22:21:30 | [maml_trainer] epoch #453 | Finished meta-testing... +2025-04-12 22:21:30 | [maml_trainer] epoch #453 | Saving snapshot... +2025-04-12 22:21:53 | [maml_trainer] epoch #453 | Saved +2025-04-12 22:21:53 | [maml_trainer] epoch #453 | Time 798157.37 s +2025-04-12 22:21:53 | [maml_trainer] epoch #453 | EpochTime 1747.67 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.2346 +Average/AverageReturn -49.189 +Average/Iteration 453 +Average/MaxReturn -36.7171 +Average/MinReturn -128.748 +Average/NumEpisodes 120 +Average/StdReturn 14.8822 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69204 +GaussianMLPPolicy/KLAfter 0.00336771 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000109619 +GaussianMLPPolicy/LossBefore 1.52985e-08 +GaussianMLPPolicy/dLoss -0.000109603 +Iteration 453 +MetaTest/Average/AverageDiscountedReturn -45.5221 +MetaTest/Average/AverageReturn -45.5221 +MetaTest/Average/Iteration 453 +MetaTest/Average/MaxReturn -37.2677 +MetaTest/Average/MinReturn -56.9127 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.78722 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.5221 +MetaTest/__unnamed_task__/AverageReturn -45.5221 +MetaTest/__unnamed_task__/Iteration 453 +MetaTest/__unnamed_task__/MaxReturn -37.2677 +MetaTest/__unnamed_task__/MinReturn -56.9127 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.78722 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1792e+07 +__unnamed_task__/AverageDiscountedReturn -25.2346 +__unnamed_task__/AverageReturn -49.189 +__unnamed_task__/Iteration 453 +__unnamed_task__/MaxReturn -36.7171 +__unnamed_task__/MinReturn -128.748 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.8822 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 22:46:42 | [maml_trainer] epoch #454 | Sampling for adapation and meta-testing... +2025-04-12 22:50:52 | [maml_trainer] epoch #454 | Finished meta-testing... +2025-04-12 22:50:52 | [maml_trainer] epoch #454 | Saving snapshot... +2025-04-12 22:51:14 | [maml_trainer] epoch #454 | Saved +2025-04-12 22:51:14 | [maml_trainer] epoch #454 | Time 799918.76 s +2025-04-12 22:51:14 | [maml_trainer] epoch #454 | EpochTime 1761.39 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1784 +Average/AverageReturn -48.5409 +Average/Iteration 454 +Average/MaxReturn -38.0776 +Average/MinReturn -118.018 +Average/NumEpisodes 120 +Average/StdReturn 12.7805 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69154 +GaussianMLPPolicy/KLAfter 0.00305489 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.32346e-05 +GaussianMLPPolicy/LossBefore -1.30335e-08 +GaussianMLPPolicy/dLoss 9.32216e-05 +Iteration 454 +MetaTest/Average/AverageDiscountedReturn -46.3252 +MetaTest/Average/AverageReturn -46.3252 +MetaTest/Average/Iteration 454 +MetaTest/Average/MaxReturn -39.4988 +MetaTest/Average/MinReturn -55.2744 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.81691 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.3252 +MetaTest/__unnamed_task__/AverageReturn -46.3252 +MetaTest/__unnamed_task__/Iteration 454 +MetaTest/__unnamed_task__/MaxReturn -39.4988 +MetaTest/__unnamed_task__/MinReturn -55.2744 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.81691 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.184e+07 +__unnamed_task__/AverageDiscountedReturn -25.1784 +__unnamed_task__/AverageReturn -48.5409 +__unnamed_task__/Iteration 454 +__unnamed_task__/MaxReturn -38.0776 +__unnamed_task__/MinReturn -118.018 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.7805 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 23:15:55 | [maml_trainer] epoch #455 | Sampling for adapation and meta-testing... +2025-04-12 23:20:01 | [maml_trainer] epoch #455 | Finished meta-testing... +2025-04-12 23:20:01 | [maml_trainer] epoch #455 | Saving snapshot... +2025-04-12 23:20:22 | [maml_trainer] epoch #455 | Saved +2025-04-12 23:20:22 | [maml_trainer] epoch #455 | Time 801666.35 s +2025-04-12 23:20:22 | [maml_trainer] epoch #455 | EpochTime 1747.59 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.877 +Average/AverageReturn -47.4779 +Average/Iteration 455 +Average/MaxReturn -38.1071 +Average/MinReturn -113.126 +Average/NumEpisodes 120 +Average/StdReturn 8.78683 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69167 +GaussianMLPPolicy/KLAfter 0.00351538 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000129939 +GaussianMLPPolicy/LossBefore 3.33786e-09 +GaussianMLPPolicy/dLoss 0.000129943 +Iteration 455 +MetaTest/Average/AverageDiscountedReturn -45.5608 +MetaTest/Average/AverageReturn -45.5608 +MetaTest/Average/Iteration 455 +MetaTest/Average/MaxReturn -38.531 +MetaTest/Average/MinReturn -58.3229 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.66354 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.5608 +MetaTest/__unnamed_task__/AverageReturn -45.5608 +MetaTest/__unnamed_task__/Iteration 455 +MetaTest/__unnamed_task__/MaxReturn -38.531 +MetaTest/__unnamed_task__/MinReturn -58.3229 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.66354 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1888e+07 +__unnamed_task__/AverageDiscountedReturn -24.877 +__unnamed_task__/AverageReturn -47.4779 +__unnamed_task__/Iteration 455 +__unnamed_task__/MaxReturn -38.1071 +__unnamed_task__/MinReturn -113.126 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.78683 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-12 23:44:46 | [maml_trainer] epoch #456 | Sampling for adapation and meta-testing... +2025-04-12 23:48:51 | [maml_trainer] epoch #456 | Finished meta-testing... +2025-04-12 23:48:51 | [maml_trainer] epoch #456 | Saving snapshot... +2025-04-12 23:49:13 | [maml_trainer] epoch #456 | Saved +2025-04-12 23:49:13 | [maml_trainer] epoch #456 | Time 803397.11 s +2025-04-12 23:49:13 | [maml_trainer] epoch #456 | EpochTime 1730.75 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.6407 +Average/AverageReturn -47.0165 +Average/Iteration 456 +Average/MaxReturn -35.3978 +Average/MinReturn -130.82 +Average/NumEpisodes 120 +Average/StdReturn 10.993 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69073 +GaussianMLPPolicy/KLAfter 0.00277673 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.73208e-05 +GaussianMLPPolicy/LossBefore -2.9405e-09 +GaussianMLPPolicy/dLoss -7.73238e-05 +Iteration 456 +MetaTest/Average/AverageDiscountedReturn -49.1142 +MetaTest/Average/AverageReturn -49.1142 +MetaTest/Average/Iteration 456 +MetaTest/Average/MaxReturn -40.3587 +MetaTest/Average/MinReturn -65.2457 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.65378 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.1142 +MetaTest/__unnamed_task__/AverageReturn -49.1142 +MetaTest/__unnamed_task__/Iteration 456 +MetaTest/__unnamed_task__/MaxReturn -40.3587 +MetaTest/__unnamed_task__/MinReturn -65.2457 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.65378 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1936e+07 +__unnamed_task__/AverageDiscountedReturn -24.6407 +__unnamed_task__/AverageReturn -47.0165 +__unnamed_task__/Iteration 456 +__unnamed_task__/MaxReturn -35.3978 +__unnamed_task__/MinReturn -130.82 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.993 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 00:13:50 | [maml_trainer] epoch #457 | Sampling for adapation and meta-testing... +2025-04-13 00:17:58 | [maml_trainer] epoch #457 | Finished meta-testing... +2025-04-13 00:17:58 | [maml_trainer] epoch #457 | Saving snapshot... +2025-04-13 00:18:20 | [maml_trainer] epoch #457 | Saved +2025-04-13 00:18:20 | [maml_trainer] epoch #457 | Time 805144.29 s +2025-04-13 00:18:20 | [maml_trainer] epoch #457 | EpochTime 1747.18 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.9935 +Average/AverageReturn -48.1974 +Average/Iteration 457 +Average/MaxReturn -38.1027 +Average/MinReturn -139.035 +Average/NumEpisodes 120 +Average/StdReturn 11.4771 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69124 +GaussianMLPPolicy/KLAfter 0.00169391 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.09106e-05 +GaussianMLPPolicy/LossBefore 5.80152e-09 +GaussianMLPPolicy/dLoss 3.09164e-05 +Iteration 457 +MetaTest/Average/AverageDiscountedReturn -49.3352 +MetaTest/Average/AverageReturn -49.3352 +MetaTest/Average/Iteration 457 +MetaTest/Average/MaxReturn -40.5382 +MetaTest/Average/MinReturn -101.369 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.3951 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.3352 +MetaTest/__unnamed_task__/AverageReturn -49.3352 +MetaTest/__unnamed_task__/Iteration 457 +MetaTest/__unnamed_task__/MaxReturn -40.5382 +MetaTest/__unnamed_task__/MinReturn -101.369 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.3951 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.1984e+07 +__unnamed_task__/AverageDiscountedReturn -24.9935 +__unnamed_task__/AverageReturn -48.1974 +__unnamed_task__/Iteration 457 +__unnamed_task__/MaxReturn -38.1027 +__unnamed_task__/MinReturn -139.035 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.4771 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 00:43:02 | [maml_trainer] epoch #458 | Sampling for adapation and meta-testing... +2025-04-13 00:47:18 | [maml_trainer] epoch #458 | Finished meta-testing... +2025-04-13 00:47:18 | [maml_trainer] epoch #458 | Saving snapshot... +2025-04-13 00:47:39 | [maml_trainer] epoch #458 | Saved +2025-04-13 00:47:39 | [maml_trainer] epoch #458 | Time 806903.89 s +2025-04-13 00:47:39 | [maml_trainer] epoch #458 | EpochTime 1759.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.3934 +Average/AverageReturn -49.4056 +Average/Iteration 458 +Average/MaxReturn -37.4562 +Average/MinReturn -125.032 +Average/NumEpisodes 120 +Average/StdReturn 13.2969 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69011 +GaussianMLPPolicy/KLAfter 0.00147652 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.18661e-05 +GaussianMLPPolicy/LossBefore 3.49681e-09 +GaussianMLPPolicy/dLoss -2.18626e-05 +Iteration 458 +MetaTest/Average/AverageDiscountedReturn -48.148 +MetaTest/Average/AverageReturn -48.148 +MetaTest/Average/Iteration 458 +MetaTest/Average/MaxReturn -39.9819 +MetaTest/Average/MinReturn -58.8253 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.44904 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.148 +MetaTest/__unnamed_task__/AverageReturn -48.148 +MetaTest/__unnamed_task__/Iteration 458 +MetaTest/__unnamed_task__/MaxReturn -39.9819 +MetaTest/__unnamed_task__/MinReturn -58.8253 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.44904 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2032e+07 +__unnamed_task__/AverageDiscountedReturn -25.3934 +__unnamed_task__/AverageReturn -49.4056 +__unnamed_task__/Iteration 458 +__unnamed_task__/MaxReturn -37.4562 +__unnamed_task__/MinReturn -125.032 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.2969 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 01:12:32 | [maml_trainer] epoch #459 | Sampling for adapation and meta-testing... +2025-04-13 01:16:38 | [maml_trainer] epoch #459 | Finished meta-testing... +2025-04-13 01:16:38 | [maml_trainer] epoch #459 | Saving snapshot... +2025-04-13 01:17:00 | [maml_trainer] epoch #459 | Saved +2025-04-13 01:17:00 | [maml_trainer] epoch #459 | Time 808664.43 s +2025-04-13 01:17:00 | [maml_trainer] epoch #459 | EpochTime 1760.53 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.4163 +Average/AverageReturn -49.2488 +Average/Iteration 459 +Average/MaxReturn -37.4941 +Average/MinReturn -127.661 +Average/NumEpisodes 120 +Average/StdReturn 11.1156 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68926 +GaussianMLPPolicy/KLAfter 0.00124072 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.75133e-05 +GaussianMLPPolicy/LossBefore -9.13938e-10 +GaussianMLPPolicy/dLoss 8.75123e-05 +Iteration 459 +MetaTest/Average/AverageDiscountedReturn -52.6029 +MetaTest/Average/AverageReturn -52.6029 +MetaTest/Average/Iteration 459 +MetaTest/Average/MaxReturn -40.6906 +MetaTest/Average/MinReturn -118.868 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.8804 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.6029 +MetaTest/__unnamed_task__/AverageReturn -52.6029 +MetaTest/__unnamed_task__/Iteration 459 +MetaTest/__unnamed_task__/MaxReturn -40.6906 +MetaTest/__unnamed_task__/MinReturn -118.868 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.8804 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.208e+07 +__unnamed_task__/AverageDiscountedReturn -25.4163 +__unnamed_task__/AverageReturn -49.2488 +__unnamed_task__/Iteration 459 +__unnamed_task__/MaxReturn -37.4941 +__unnamed_task__/MinReturn -127.661 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.1156 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 01:54:09 | [maml_trainer] epoch #460 | Sampling for adapation and meta-testing... +2025-04-13 02:01:27 | [maml_trainer] epoch #460 | Finished meta-testing... +2025-04-13 02:01:27 | [maml_trainer] epoch #460 | Saving snapshot... +2025-04-13 02:02:07 | [maml_trainer] epoch #460 | Saved +2025-04-13 02:02:07 | [maml_trainer] epoch #460 | Time 811371.66 s +2025-04-13 02:02:07 | [maml_trainer] epoch #460 | EpochTime 2707.22 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.6085 +Average/AverageReturn -50.0782 +Average/Iteration 460 +Average/MaxReturn -37.7344 +Average/MinReturn -122.189 +Average/NumEpisodes 120 +Average/StdReturn 12.3223 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68987 +GaussianMLPPolicy/KLAfter 0.00132837 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.1048e-05 +GaussianMLPPolicy/LossBefore -9.73542e-09 +GaussianMLPPolicy/dLoss 3.10382e-05 +Iteration 460 +MetaTest/Average/AverageDiscountedReturn -47.4393 +MetaTest/Average/AverageReturn -47.4393 +MetaTest/Average/Iteration 460 +MetaTest/Average/MaxReturn -37.4736 +MetaTest/Average/MinReturn -62.802 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.09797 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4393 +MetaTest/__unnamed_task__/AverageReturn -47.4393 +MetaTest/__unnamed_task__/Iteration 460 +MetaTest/__unnamed_task__/MaxReturn -37.4736 +MetaTest/__unnamed_task__/MinReturn -62.802 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.09797 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2128e+07 +__unnamed_task__/AverageDiscountedReturn -25.6085 +__unnamed_task__/AverageReturn -50.0782 +__unnamed_task__/Iteration 460 +__unnamed_task__/MaxReturn -37.7344 +__unnamed_task__/MinReturn -122.189 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.3223 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 02:46:42 | [maml_trainer] epoch #461 | Sampling for adapation and meta-testing... +2025-04-13 02:53:52 | [maml_trainer] epoch #461 | Finished meta-testing... +2025-04-13 02:53:52 | [maml_trainer] epoch #461 | Saving snapshot... +2025-04-13 02:54:33 | [maml_trainer] epoch #461 | Saved +2025-04-13 02:54:33 | [maml_trainer] epoch #461 | Time 814517.03 s +2025-04-13 02:54:33 | [maml_trainer] epoch #461 | EpochTime 3145.37 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1848 +Average/AverageReturn -48.7047 +Average/Iteration 461 +Average/MaxReturn -36.8366 +Average/MinReturn -126.01 +Average/NumEpisodes 120 +Average/StdReturn 11.5304 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69072 +GaussianMLPPolicy/KLAfter 0.00130342 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.75346e-05 +GaussianMLPPolicy/LossBefore -7.35124e-09 +GaussianMLPPolicy/dLoss 3.75273e-05 +Iteration 461 +MetaTest/Average/AverageDiscountedReturn -50.551 +MetaTest/Average/AverageReturn -50.551 +MetaTest/Average/Iteration 461 +MetaTest/Average/MaxReturn -39.2442 +MetaTest/Average/MinReturn -97.229 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 13.5349 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.551 +MetaTest/__unnamed_task__/AverageReturn -50.551 +MetaTest/__unnamed_task__/Iteration 461 +MetaTest/__unnamed_task__/MaxReturn -39.2442 +MetaTest/__unnamed_task__/MinReturn -97.229 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 13.5349 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2176e+07 +__unnamed_task__/AverageDiscountedReturn -25.1848 +__unnamed_task__/AverageReturn -48.7047 +__unnamed_task__/Iteration 461 +__unnamed_task__/MaxReturn -36.8366 +__unnamed_task__/MinReturn -126.01 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.5304 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 03:37:41 | [maml_trainer] epoch #462 | Sampling for adapation and meta-testing... +2025-04-13 03:43:17 | [maml_trainer] epoch #462 | Finished meta-testing... +2025-04-13 03:43:17 | [maml_trainer] epoch #462 | Saving snapshot... +2025-04-13 03:43:47 | [maml_trainer] epoch #462 | Saved +2025-04-13 03:43:47 | [maml_trainer] epoch #462 | Time 817471.14 s +2025-04-13 03:43:47 | [maml_trainer] epoch #462 | EpochTime 2954.10 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1804 +Average/AverageReturn -49.1083 +Average/Iteration 462 +Average/MaxReturn -37.3771 +Average/MinReturn -118.371 +Average/NumEpisodes 120 +Average/StdReturn 12.7197 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69116 +GaussianMLPPolicy/KLAfter 0.000722662 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.59724e-05 +GaussianMLPPolicy/LossBefore 6.27836e-09 +GaussianMLPPolicy/dLoss -1.59661e-05 +Iteration 462 +MetaTest/Average/AverageDiscountedReturn -43.2431 +MetaTest/Average/AverageReturn -43.2431 +MetaTest/Average/Iteration 462 +MetaTest/Average/MaxReturn -37.3407 +MetaTest/Average/MinReturn -55.4537 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.28769 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -43.2431 +MetaTest/__unnamed_task__/AverageReturn -43.2431 +MetaTest/__unnamed_task__/Iteration 462 +MetaTest/__unnamed_task__/MaxReturn -37.3407 +MetaTest/__unnamed_task__/MinReturn -55.4537 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.28769 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2224e+07 +__unnamed_task__/AverageDiscountedReturn -25.1804 +__unnamed_task__/AverageReturn -49.1083 +__unnamed_task__/Iteration 462 +__unnamed_task__/MaxReturn -37.3771 +__unnamed_task__/MinReturn -118.371 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.7197 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 04:12:00 | [maml_trainer] epoch #463 | Sampling for adapation and meta-testing... +2025-04-13 04:16:11 | [maml_trainer] epoch #463 | Finished meta-testing... +2025-04-13 04:16:11 | [maml_trainer] epoch #463 | Saving snapshot... +2025-04-13 04:16:32 | [maml_trainer] epoch #463 | Saved +2025-04-13 04:16:32 | [maml_trainer] epoch #463 | Time 819436.71 s +2025-04-13 04:16:32 | [maml_trainer] epoch #463 | EpochTime 1965.57 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.82 +Average/AverageReturn -50.6225 +Average/Iteration 463 +Average/MaxReturn -37.5319 +Average/MinReturn -138.65 +Average/NumEpisodes 120 +Average/StdReturn 14.7081 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69148 +GaussianMLPPolicy/KLAfter 0.00106157 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.66108e-06 +GaussianMLPPolicy/LossBefore -1.6133e-08 +GaussianMLPPolicy/dLoss 4.64495e-06 +Iteration 463 +MetaTest/Average/AverageDiscountedReturn -52.3429 +MetaTest/Average/AverageReturn -52.3429 +MetaTest/Average/Iteration 463 +MetaTest/Average/MaxReturn -37.4231 +MetaTest/Average/MinReturn -112.268 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 18.1367 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -52.3429 +MetaTest/__unnamed_task__/AverageReturn -52.3429 +MetaTest/__unnamed_task__/Iteration 463 +MetaTest/__unnamed_task__/MaxReturn -37.4231 +MetaTest/__unnamed_task__/MinReturn -112.268 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 18.1367 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2272e+07 +__unnamed_task__/AverageDiscountedReturn -25.82 +__unnamed_task__/AverageReturn -50.6225 +__unnamed_task__/Iteration 463 +__unnamed_task__/MaxReturn -37.5319 +__unnamed_task__/MinReturn -138.65 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.7081 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 04:41:34 | [maml_trainer] epoch #464 | Sampling for adapation and meta-testing... +2025-04-13 04:45:45 | [maml_trainer] epoch #464 | Finished meta-testing... +2025-04-13 04:45:45 | [maml_trainer] epoch #464 | Saving snapshot... +2025-04-13 04:46:08 | [maml_trainer] epoch #464 | Saved +2025-04-13 04:46:08 | [maml_trainer] epoch #464 | Time 821212.11 s +2025-04-13 04:46:08 | [maml_trainer] epoch #464 | EpochTime 1775.40 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.0981 +Average/AverageReturn -49.0219 +Average/Iteration 464 +Average/MaxReturn -38.1135 +Average/MinReturn -126.116 +Average/NumEpisodes 120 +Average/StdReturn 14.604 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69176 +GaussianMLPPolicy/KLAfter 0.000619828 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.84946e-05 +GaussianMLPPolicy/LossBefore 1.03315e-09 +GaussianMLPPolicy/dLoss -3.84936e-05 +Iteration 464 +MetaTest/Average/AverageDiscountedReturn -47.3716 +MetaTest/Average/AverageReturn -47.3716 +MetaTest/Average/Iteration 464 +MetaTest/Average/MaxReturn -38.7987 +MetaTest/Average/MinReturn -59.3521 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.14507 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.3716 +MetaTest/__unnamed_task__/AverageReturn -47.3716 +MetaTest/__unnamed_task__/Iteration 464 +MetaTest/__unnamed_task__/MaxReturn -38.7987 +MetaTest/__unnamed_task__/MinReturn -59.3521 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.14507 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.232e+07 +__unnamed_task__/AverageDiscountedReturn -25.0981 +__unnamed_task__/AverageReturn -49.0219 +__unnamed_task__/Iteration 464 +__unnamed_task__/MaxReturn -38.1135 +__unnamed_task__/MinReturn -126.116 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.604 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 05:10:48 | [maml_trainer] epoch #465 | Sampling for adapation and meta-testing... +2025-04-13 05:14:55 | [maml_trainer] epoch #465 | Finished meta-testing... +2025-04-13 05:14:55 | [maml_trainer] epoch #465 | Saving snapshot... +2025-04-13 05:15:17 | [maml_trainer] epoch #465 | Saved +2025-04-13 05:15:17 | [maml_trainer] epoch #465 | Time 822961.24 s +2025-04-13 05:15:17 | [maml_trainer] epoch #465 | EpochTime 1749.12 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.9351 +Average/AverageReturn -48.3196 +Average/Iteration 465 +Average/MaxReturn -37.6069 +Average/MinReturn -135.705 +Average/NumEpisodes 120 +Average/StdReturn 12.8316 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69191 +GaussianMLPPolicy/KLAfter 0.00134824 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.78283e-06 +GaussianMLPPolicy/LossBefore -5.36442e-09 +GaussianMLPPolicy/dLoss -9.7882e-06 +Iteration 465 +MetaTest/Average/AverageDiscountedReturn -50.7057 +MetaTest/Average/AverageReturn -50.7057 +MetaTest/Average/Iteration 465 +MetaTest/Average/MaxReturn -38.1333 +MetaTest/Average/MinReturn -111.617 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 15.1227 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.7057 +MetaTest/__unnamed_task__/AverageReturn -50.7057 +MetaTest/__unnamed_task__/Iteration 465 +MetaTest/__unnamed_task__/MaxReturn -38.1333 +MetaTest/__unnamed_task__/MinReturn -111.617 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 15.1227 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2368e+07 +__unnamed_task__/AverageDiscountedReturn -24.9351 +__unnamed_task__/AverageReturn -48.3196 +__unnamed_task__/Iteration 465 +__unnamed_task__/MaxReturn -37.6069 +__unnamed_task__/MinReturn -135.705 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.8316 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 05:40:08 | [maml_trainer] epoch #466 | Sampling for adapation and meta-testing... +2025-04-13 05:44:16 | [maml_trainer] epoch #466 | Finished meta-testing... +2025-04-13 05:44:16 | [maml_trainer] epoch #466 | Saving snapshot... +2025-04-13 05:44:37 | [maml_trainer] epoch #466 | Saved +2025-04-13 05:44:37 | [maml_trainer] epoch #466 | Time 824721.45 s +2025-04-13 05:44:37 | [maml_trainer] epoch #466 | EpochTime 1760.20 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1705 +Average/AverageReturn -49.0755 +Average/Iteration 466 +Average/MaxReturn -35.7172 +Average/MinReturn -123.401 +Average/NumEpisodes 120 +Average/StdReturn 14.2257 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69218 +GaussianMLPPolicy/KLAfter 0.00135775 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.64227e-05 +GaussianMLPPolicy/LossBefore -8.42412e-09 +GaussianMLPPolicy/dLoss 3.64143e-05 +Iteration 466 +MetaTest/Average/AverageDiscountedReturn -51.8893 +MetaTest/Average/AverageReturn -51.8893 +MetaTest/Average/Iteration 466 +MetaTest/Average/MaxReturn -40.5762 +MetaTest/Average/MinReturn -105.642 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.5446 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.8893 +MetaTest/__unnamed_task__/AverageReturn -51.8893 +MetaTest/__unnamed_task__/Iteration 466 +MetaTest/__unnamed_task__/MaxReturn -40.5762 +MetaTest/__unnamed_task__/MinReturn -105.642 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.5446 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2416e+07 +__unnamed_task__/AverageDiscountedReturn -25.1705 +__unnamed_task__/AverageReturn -49.0755 +__unnamed_task__/Iteration 466 +__unnamed_task__/MaxReturn -35.7172 +__unnamed_task__/MinReturn -123.401 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.2257 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 06:09:14 | [maml_trainer] epoch #467 | Sampling for adapation and meta-testing... +2025-04-13 06:13:27 | [maml_trainer] epoch #467 | Finished meta-testing... +2025-04-13 06:13:27 | [maml_trainer] epoch #467 | Saving snapshot... +2025-04-13 06:13:50 | [maml_trainer] epoch #467 | Saved +2025-04-13 06:13:50 | [maml_trainer] epoch #467 | Time 826474.35 s +2025-04-13 06:13:50 | [maml_trainer] epoch #467 | EpochTime 1752.90 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.9916 +Average/AverageReturn -48.202 +Average/Iteration 467 +Average/MaxReturn -37.1279 +Average/MinReturn -101.01 +Average/NumEpisodes 120 +Average/StdReturn 10.3615 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69171 +GaussianMLPPolicy/KLAfter 0.00212855 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000100398 +GaussianMLPPolicy/LossBefore -1.41859e-08 +GaussianMLPPolicy/dLoss -0.000100412 +Iteration 467 +MetaTest/Average/AverageDiscountedReturn -46.689 +MetaTest/Average/AverageReturn -46.689 +MetaTest/Average/Iteration 467 +MetaTest/Average/MaxReturn -38.3238 +MetaTest/Average/MinReturn -62.6795 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.07676 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.689 +MetaTest/__unnamed_task__/AverageReturn -46.689 +MetaTest/__unnamed_task__/Iteration 467 +MetaTest/__unnamed_task__/MaxReturn -38.3238 +MetaTest/__unnamed_task__/MinReturn -62.6795 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.07676 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2464e+07 +__unnamed_task__/AverageDiscountedReturn -24.9916 +__unnamed_task__/AverageReturn -48.202 +__unnamed_task__/Iteration 467 +__unnamed_task__/MaxReturn -37.1279 +__unnamed_task__/MinReturn -101.01 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 10.3615 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 06:38:36 | [maml_trainer] epoch #468 | Sampling for adapation and meta-testing... +2025-04-13 06:42:43 | [maml_trainer] epoch #468 | Finished meta-testing... +2025-04-13 06:42:43 | [maml_trainer] epoch #468 | Saving snapshot... +2025-04-13 06:43:04 | [maml_trainer] epoch #468 | Saved +2025-04-13 06:43:04 | [maml_trainer] epoch #468 | Time 828228.51 s +2025-04-13 06:43:04 | [maml_trainer] epoch #468 | EpochTime 1754.16 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.2551 +Average/AverageReturn -49.4234 +Average/Iteration 468 +Average/MaxReturn -37.4976 +Average/MinReturn -130.023 +Average/NumEpisodes 120 +Average/StdReturn 14.9268 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69148 +GaussianMLPPolicy/KLAfter 0.00268117 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 3.26095e-05 +GaussianMLPPolicy/LossBefore -3.8147e-09 +GaussianMLPPolicy/dLoss -3.26133e-05 +Iteration 468 +MetaTest/Average/AverageDiscountedReturn -54.4013 +MetaTest/Average/AverageReturn -54.4013 +MetaTest/Average/Iteration 468 +MetaTest/Average/MaxReturn -37.7363 +MetaTest/Average/MinReturn -117.829 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 22.1579 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.4013 +MetaTest/__unnamed_task__/AverageReturn -54.4013 +MetaTest/__unnamed_task__/Iteration 468 +MetaTest/__unnamed_task__/MaxReturn -37.7363 +MetaTest/__unnamed_task__/MinReturn -117.829 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 22.1579 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2512e+07 +__unnamed_task__/AverageDiscountedReturn -25.2551 +__unnamed_task__/AverageReturn -49.4234 +__unnamed_task__/Iteration 468 +__unnamed_task__/MaxReturn -37.4976 +__unnamed_task__/MinReturn -130.023 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.9268 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 07:07:56 | [maml_trainer] epoch #469 | Sampling for adapation and meta-testing... +2025-04-13 07:12:02 | [maml_trainer] epoch #469 | Finished meta-testing... +2025-04-13 07:12:02 | [maml_trainer] epoch #469 | Saving snapshot... +2025-04-13 07:12:23 | [maml_trainer] epoch #469 | Saved +2025-04-13 07:12:23 | [maml_trainer] epoch #469 | Time 829987.65 s +2025-04-13 07:12:23 | [maml_trainer] epoch #469 | EpochTime 1759.14 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.3998 +Average/AverageReturn -50.0614 +Average/Iteration 469 +Average/MaxReturn -35.0622 +Average/MinReturn -144.91 +Average/NumEpisodes 120 +Average/StdReturn 16.5334 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69063 +GaussianMLPPolicy/KLAfter 0.00510049 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.92011e-05 +GaussianMLPPolicy/LossBefore -6.07967e-09 +GaussianMLPPolicy/dLoss -7.92072e-05 +Iteration 469 +MetaTest/Average/AverageDiscountedReturn -46.4231 +MetaTest/Average/AverageReturn -46.4231 +MetaTest/Average/Iteration 469 +MetaTest/Average/MaxReturn -38.3078 +MetaTest/Average/MinReturn -65.5556 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.02133 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.4231 +MetaTest/__unnamed_task__/AverageReturn -46.4231 +MetaTest/__unnamed_task__/Iteration 469 +MetaTest/__unnamed_task__/MaxReturn -38.3078 +MetaTest/__unnamed_task__/MinReturn -65.5556 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.02133 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.256e+07 +__unnamed_task__/AverageDiscountedReturn -25.3998 +__unnamed_task__/AverageReturn -50.0614 +__unnamed_task__/Iteration 469 +__unnamed_task__/MaxReturn -35.0622 +__unnamed_task__/MinReturn -144.91 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.5334 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 07:37:12 | [maml_trainer] epoch #470 | Sampling for adapation and meta-testing... +2025-04-13 07:41:20 | [maml_trainer] epoch #470 | Finished meta-testing... +2025-04-13 07:41:20 | [maml_trainer] epoch #470 | Saving snapshot... +2025-04-13 07:41:42 | [maml_trainer] epoch #470 | Saved +2025-04-13 07:41:42 | [maml_trainer] epoch #470 | Time 831746.67 s +2025-04-13 07:41:42 | [maml_trainer] epoch #470 | EpochTime 1759.02 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.8804 +Average/AverageReturn -52.9804 +Average/Iteration 470 +Average/MaxReturn -37.2287 +Average/MinReturn -157.391 +Average/NumEpisodes 120 +Average/StdReturn 19.9632 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68946 +GaussianMLPPolicy/KLAfter 0.00824071 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.55242e-05 +GaussianMLPPolicy/LossBefore 1.47025e-09 +GaussianMLPPolicy/dLoss 1.55257e-05 +Iteration 470 +MetaTest/Average/AverageDiscountedReturn -49.7106 +MetaTest/Average/AverageReturn -49.7106 +MetaTest/Average/Iteration 470 +MetaTest/Average/MaxReturn -38.3264 +MetaTest/Average/MinReturn -108.912 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.1784 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7106 +MetaTest/__unnamed_task__/AverageReturn -49.7106 +MetaTest/__unnamed_task__/Iteration 470 +MetaTest/__unnamed_task__/MaxReturn -38.3264 +MetaTest/__unnamed_task__/MinReturn -108.912 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.1784 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2608e+07 +__unnamed_task__/AverageDiscountedReturn -25.8804 +__unnamed_task__/AverageReturn -52.9804 +__unnamed_task__/Iteration 470 +__unnamed_task__/MaxReturn -37.2287 +__unnamed_task__/MinReturn -157.391 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 19.9632 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 08:06:18 | [maml_trainer] epoch #471 | Sampling for adapation and meta-testing... +2025-04-13 08:10:23 | [maml_trainer] epoch #471 | Finished meta-testing... +2025-04-13 08:10:23 | [maml_trainer] epoch #471 | Saving snapshot... +2025-04-13 08:10:45 | [maml_trainer] epoch #471 | Saved +2025-04-13 08:10:45 | [maml_trainer] epoch #471 | Time 833489.42 s +2025-04-13 08:10:45 | [maml_trainer] epoch #471 | EpochTime 1742.75 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1159 +Average/AverageReturn -51.5196 +Average/Iteration 471 +Average/MaxReturn -35.931 +Average/MinReturn -147.675 +Average/NumEpisodes 120 +Average/StdReturn 19.7965 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68864 +GaussianMLPPolicy/KLAfter 0.0040371 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.37884e-05 +GaussianMLPPolicy/LossBefore -4.15246e-09 +GaussianMLPPolicy/dLoss -8.37926e-05 +Iteration 471 +MetaTest/Average/AverageDiscountedReturn -63.2981 +MetaTest/Average/AverageReturn -63.2981 +MetaTest/Average/Iteration 471 +MetaTest/Average/MaxReturn -38.9344 +MetaTest/Average/MinReturn -136.237 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 29.5742 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -63.2981 +MetaTest/__unnamed_task__/AverageReturn -63.2981 +MetaTest/__unnamed_task__/Iteration 471 +MetaTest/__unnamed_task__/MaxReturn -38.9344 +MetaTest/__unnamed_task__/MinReturn -136.237 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 29.5742 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2656e+07 +__unnamed_task__/AverageDiscountedReturn -25.1159 +__unnamed_task__/AverageReturn -51.5196 +__unnamed_task__/Iteration 471 +__unnamed_task__/MaxReturn -35.931 +__unnamed_task__/MinReturn -147.675 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 19.7965 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 08:35:26 | [maml_trainer] epoch #472 | Sampling for adapation and meta-testing... +2025-04-13 08:39:38 | [maml_trainer] epoch #472 | Finished meta-testing... +2025-04-13 08:39:38 | [maml_trainer] epoch #472 | Saving snapshot... +2025-04-13 08:40:00 | [maml_trainer] epoch #472 | Saved +2025-04-13 08:40:00 | [maml_trainer] epoch #472 | Time 835244.67 s +2025-04-13 08:40:00 | [maml_trainer] epoch #472 | EpochTime 1755.24 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.3991 +Average/AverageReturn -52.5674 +Average/Iteration 472 +Average/MaxReturn -34.957 +Average/MinReturn -152.502 +Average/NumEpisodes 120 +Average/StdReturn 21.8751 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68808 +GaussianMLPPolicy/KLAfter 0.00335697 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.09724e-06 +GaussianMLPPolicy/LossBefore -7.94729e-11 +GaussianMLPPolicy/dLoss -1.09732e-06 +Iteration 472 +MetaTest/Average/AverageDiscountedReturn -51.3768 +MetaTest/Average/AverageReturn -51.3768 +MetaTest/Average/Iteration 472 +MetaTest/Average/MaxReturn -38.1489 +MetaTest/Average/MinReturn -124.342 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.7945 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.3768 +MetaTest/__unnamed_task__/AverageReturn -51.3768 +MetaTest/__unnamed_task__/Iteration 472 +MetaTest/__unnamed_task__/MaxReturn -38.1489 +MetaTest/__unnamed_task__/MinReturn -124.342 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.7945 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2704e+07 +__unnamed_task__/AverageDiscountedReturn -25.3991 +__unnamed_task__/AverageReturn -52.5674 +__unnamed_task__/Iteration 472 +__unnamed_task__/MaxReturn -34.957 +__unnamed_task__/MinReturn -152.502 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 21.8751 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 09:04:39 | [maml_trainer] epoch #473 | Sampling for adapation and meta-testing... +2025-04-13 09:08:51 | [maml_trainer] epoch #473 | Finished meta-testing... +2025-04-13 09:08:51 | [maml_trainer] epoch #473 | Saving snapshot... +2025-04-13 09:09:12 | [maml_trainer] epoch #473 | Saved +2025-04-13 09:09:12 | [maml_trainer] epoch #473 | Time 836996.27 s +2025-04-13 09:09:12 | [maml_trainer] epoch #473 | EpochTime 1751.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.639 +Average/AverageReturn -48.6053 +Average/Iteration 473 +Average/MaxReturn -34.8489 +Average/MinReturn -135.065 +Average/NumEpisodes 120 +Average/StdReturn 14.2276 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68796 +GaussianMLPPolicy/KLAfter 0.00247317 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.09965e-05 +GaussianMLPPolicy/LossBefore 3.41733e-09 +GaussianMLPPolicy/dLoss 1.1e-05 +Iteration 473 +MetaTest/Average/AverageDiscountedReturn -48.1697 +MetaTest/Average/AverageReturn -48.1697 +MetaTest/Average/Iteration 473 +MetaTest/Average/MaxReturn -37.6256 +MetaTest/Average/MinReturn -72.9055 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 8.68649 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -48.1697 +MetaTest/__unnamed_task__/AverageReturn -48.1697 +MetaTest/__unnamed_task__/Iteration 473 +MetaTest/__unnamed_task__/MaxReturn -37.6256 +MetaTest/__unnamed_task__/MinReturn -72.9055 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 8.68649 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2752e+07 +__unnamed_task__/AverageDiscountedReturn -24.639 +__unnamed_task__/AverageReturn -48.6053 +__unnamed_task__/Iteration 473 +__unnamed_task__/MaxReturn -34.8489 +__unnamed_task__/MinReturn -135.065 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 14.2276 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 09:33:50 | [maml_trainer] epoch #474 | Sampling for adapation and meta-testing... +2025-04-13 09:37:54 | [maml_trainer] epoch #474 | Finished meta-testing... +2025-04-13 09:37:54 | [maml_trainer] epoch #474 | Saving snapshot... +2025-04-13 09:38:16 | [maml_trainer] epoch #474 | Saved +2025-04-13 09:38:16 | [maml_trainer] epoch #474 | Time 838740.27 s +2025-04-13 09:38:16 | [maml_trainer] epoch #474 | EpochTime 1744.00 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.2977 +Average/AverageReturn -51.1657 +Average/Iteration 474 +Average/MaxReturn -35.9761 +Average/MinReturn -142.516 +Average/NumEpisodes 120 +Average/StdReturn 20.0056 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68809 +GaussianMLPPolicy/KLAfter 0.00233404 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000100223 +GaussianMLPPolicy/LossBefore -7.90755e-09 +GaussianMLPPolicy/dLoss 0.000100215 +Iteration 474 +MetaTest/Average/AverageDiscountedReturn -49.9986 +MetaTest/Average/AverageReturn -49.9986 +MetaTest/Average/Iteration 474 +MetaTest/Average/MaxReturn -37.6338 +MetaTest/Average/MinReturn -134.061 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 20.2617 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9986 +MetaTest/__unnamed_task__/AverageReturn -49.9986 +MetaTest/__unnamed_task__/Iteration 474 +MetaTest/__unnamed_task__/MaxReturn -37.6338 +MetaTest/__unnamed_task__/MinReturn -134.061 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 20.2617 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.28e+07 +__unnamed_task__/AverageDiscountedReturn -25.2977 +__unnamed_task__/AverageReturn -51.1657 +__unnamed_task__/Iteration 474 +__unnamed_task__/MaxReturn -35.9761 +__unnamed_task__/MinReturn -142.516 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.0056 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 10:02:46 | [maml_trainer] epoch #475 | Sampling for adapation and meta-testing... +2025-04-13 10:06:53 | [maml_trainer] epoch #475 | Finished meta-testing... +2025-04-13 10:06:53 | [maml_trainer] epoch #475 | Saving snapshot... +2025-04-13 10:07:15 | [maml_trainer] epoch #475 | Saved +2025-04-13 10:07:15 | [maml_trainer] epoch #475 | Time 840479.87 s +2025-04-13 10:07:15 | [maml_trainer] epoch #475 | EpochTime 1739.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.4161 +Average/AverageReturn -48.4703 +Average/Iteration 475 +Average/MaxReturn -35.9097 +Average/MinReturn -117.167 +Average/NumEpisodes 120 +Average/StdReturn 13.6475 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68844 +GaussianMLPPolicy/KLAfter 0.00341142 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.21033e-05 +GaussianMLPPolicy/LossBefore 8.52346e-09 +GaussianMLPPolicy/dLoss 3.21118e-05 +Iteration 475 +MetaTest/Average/AverageDiscountedReturn -49.9938 +MetaTest/Average/AverageReturn -49.9938 +MetaTest/Average/Iteration 475 +MetaTest/Average/MaxReturn -38.6739 +MetaTest/Average/MinReturn -90.5431 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.6909 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.9938 +MetaTest/__unnamed_task__/AverageReturn -49.9938 +MetaTest/__unnamed_task__/Iteration 475 +MetaTest/__unnamed_task__/MaxReturn -38.6739 +MetaTest/__unnamed_task__/MinReturn -90.5431 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.6909 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2848e+07 +__unnamed_task__/AverageDiscountedReturn -24.4161 +__unnamed_task__/AverageReturn -48.4703 +__unnamed_task__/Iteration 475 +__unnamed_task__/MaxReturn -35.9097 +__unnamed_task__/MinReturn -117.167 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.6475 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 10:32:03 | [maml_trainer] epoch #476 | Sampling for adapation and meta-testing... +2025-04-13 10:36:12 | [maml_trainer] epoch #476 | Finished meta-testing... +2025-04-13 10:36:12 | [maml_trainer] epoch #476 | Saving snapshot... +2025-04-13 10:36:33 | [maml_trainer] epoch #476 | Saved +2025-04-13 10:36:33 | [maml_trainer] epoch #476 | Time 842237.45 s +2025-04-13 10:36:33 | [maml_trainer] epoch #476 | EpochTime 1757.58 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.4456 +Average/AverageReturn -47.8469 +Average/Iteration 476 +Average/MaxReturn -36.0614 +Average/MinReturn -144.133 +Average/NumEpisodes 120 +Average/StdReturn 13.9006 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6882 +GaussianMLPPolicy/KLAfter 0.0027002 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.23435e-05 +GaussianMLPPolicy/LossBefore 6.63598e-09 +GaussianMLPPolicy/dLoss 5.23502e-05 +Iteration 476 +MetaTest/Average/AverageDiscountedReturn -49.8064 +MetaTest/Average/AverageReturn -49.8064 +MetaTest/Average/Iteration 476 +MetaTest/Average/MaxReturn -40.3387 +MetaTest/Average/MinReturn -69.6496 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.34713 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8064 +MetaTest/__unnamed_task__/AverageReturn -49.8064 +MetaTest/__unnamed_task__/Iteration 476 +MetaTest/__unnamed_task__/MaxReturn -40.3387 +MetaTest/__unnamed_task__/MinReturn -69.6496 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.34713 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2896e+07 +__unnamed_task__/AverageDiscountedReturn -24.4456 +__unnamed_task__/AverageReturn -47.8469 +__unnamed_task__/Iteration 476 +__unnamed_task__/MaxReturn -36.0614 +__unnamed_task__/MinReturn -144.133 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 13.9006 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 11:01:09 | [maml_trainer] epoch #477 | Sampling for adapation and meta-testing... +2025-04-13 11:05:15 | [maml_trainer] epoch #477 | Finished meta-testing... +2025-04-13 11:05:15 | [maml_trainer] epoch #477 | Saving snapshot... +2025-04-13 11:05:37 | [maml_trainer] epoch #477 | Saved +2025-04-13 11:05:37 | [maml_trainer] epoch #477 | Time 843981.28 s +2025-04-13 11:05:37 | [maml_trainer] epoch #477 | EpochTime 1743.83 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.012 +Average/AverageReturn -50.3534 +Average/Iteration 477 +Average/MaxReturn -34.874 +Average/MinReturn -143.596 +Average/NumEpisodes 120 +Average/StdReturn 18.8437 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68914 +GaussianMLPPolicy/KLAfter 0.00218556 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.94811e-05 +GaussianMLPPolicy/LossBefore 6.79493e-09 +GaussianMLPPolicy/dLoss 2.94879e-05 +Iteration 477 +MetaTest/Average/AverageDiscountedReturn -53.4059 +MetaTest/Average/AverageReturn -53.4059 +MetaTest/Average/Iteration 477 +MetaTest/Average/MaxReturn -40.1869 +MetaTest/Average/MinReturn -156.932 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.47 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.4059 +MetaTest/__unnamed_task__/AverageReturn -53.4059 +MetaTest/__unnamed_task__/Iteration 477 +MetaTest/__unnamed_task__/MaxReturn -40.1869 +MetaTest/__unnamed_task__/MinReturn -156.932 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.47 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2944e+07 +__unnamed_task__/AverageDiscountedReturn -25.012 +__unnamed_task__/AverageReturn -50.3534 +__unnamed_task__/Iteration 477 +__unnamed_task__/MaxReturn -34.874 +__unnamed_task__/MinReturn -143.596 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 18.8437 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 11:30:06 | [maml_trainer] epoch #478 | Sampling for adapation and meta-testing... +2025-04-13 11:34:12 | [maml_trainer] epoch #478 | Finished meta-testing... +2025-04-13 11:34:12 | [maml_trainer] epoch #478 | Saving snapshot... +2025-04-13 11:34:33 | [maml_trainer] epoch #478 | Saved +2025-04-13 11:34:33 | [maml_trainer] epoch #478 | Time 845717.26 s +2025-04-13 11:34:33 | [maml_trainer] epoch #478 | EpochTime 1735.97 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.7128 +Average/AverageReturn -48.0374 +Average/Iteration 478 +Average/MaxReturn -35.026 +Average/MinReturn -83.6475 +Average/NumEpisodes 120 +Average/StdReturn 7.75657 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68967 +GaussianMLPPolicy/KLAfter 0.00243361 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 7.47247e-05 +GaussianMLPPolicy/LossBefore 2.05835e-08 +GaussianMLPPolicy/dLoss -7.47041e-05 +Iteration 478 +MetaTest/Average/AverageDiscountedReturn -46.5951 +MetaTest/Average/AverageReturn -46.5951 +MetaTest/Average/Iteration 478 +MetaTest/Average/MaxReturn -39.0783 +MetaTest/Average/MinReturn -56.4781 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 4.38924 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.5951 +MetaTest/__unnamed_task__/AverageReturn -46.5951 +MetaTest/__unnamed_task__/Iteration 478 +MetaTest/__unnamed_task__/MaxReturn -39.0783 +MetaTest/__unnamed_task__/MinReturn -56.4781 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 4.38924 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.2992e+07 +__unnamed_task__/AverageDiscountedReturn -24.7128 +__unnamed_task__/AverageReturn -48.0374 +__unnamed_task__/Iteration 478 +__unnamed_task__/MaxReturn -35.026 +__unnamed_task__/MinReturn -83.6475 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 7.75657 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-13 11:58:55 | [maml_trainer] epoch #479 | Sampling for adapation and meta-testing... +2025-04-13 12:02:54 | [maml_trainer] epoch #479 | Finished meta-testing... +2025-04-13 12:02:54 | [maml_trainer] epoch #479 | Saving snapshot... +2025-04-13 12:03:15 | [maml_trainer] epoch #479 | Saved +2025-04-13 12:03:15 | [maml_trainer] epoch #479 | Time 847439.85 s +2025-04-13 12:03:15 | [maml_trainer] epoch #479 | EpochTime 1722.59 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.5712 +Average/AverageReturn -47.836 +Average/Iteration 479 +Average/MaxReturn -37.2019 +Average/MinReturn -84.5094 +Average/NumEpisodes 120 +Average/StdReturn 8.06228 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69031 +GaussianMLPPolicy/KLAfter 0.00299514 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -7.91701e-06 +GaussianMLPPolicy/LossBefore 4.60943e-09 +GaussianMLPPolicy/dLoss 7.92162e-06 +Iteration 479 +MetaTest/Average/AverageDiscountedReturn -49.8231 +MetaTest/Average/AverageReturn -49.8231 +MetaTest/Average/Iteration 479 +MetaTest/Average/MaxReturn -38.8096 +MetaTest/Average/MinReturn -82.1697 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 11.2153 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.8231 +MetaTest/__unnamed_task__/AverageReturn -49.8231 +MetaTest/__unnamed_task__/Iteration 479 +MetaTest/__unnamed_task__/MaxReturn -38.8096 +MetaTest/__unnamed_task__/MinReturn -82.1697 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 11.2153 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.304e+07 +__unnamed_task__/AverageDiscountedReturn -24.5712 +__unnamed_task__/AverageReturn -47.836 +__unnamed_task__/Iteration 479 +__unnamed_task__/MaxReturn -37.2019 +__unnamed_task__/MinReturn -84.5094 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 8.06228 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-13 12:27:22 | [maml_trainer] epoch #480 | Sampling for adapation and meta-testing... +2025-04-13 12:31:22 | [maml_trainer] epoch #480 | Finished meta-testing... +2025-04-13 12:31:22 | [maml_trainer] epoch #480 | Saving snapshot... +2025-04-13 12:31:44 | [maml_trainer] epoch #480 | Saved +2025-04-13 12:31:44 | [maml_trainer] epoch #480 | Time 849148.54 s +2025-04-13 12:31:44 | [maml_trainer] epoch #480 | EpochTime 1708.69 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.119 +Average/AverageReturn -49.3903 +Average/Iteration 480 +Average/MaxReturn -37.3337 +Average/MinReturn -103.975 +Average/NumEpisodes 120 +Average/StdReturn 9.01486 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69185 +GaussianMLPPolicy/KLAfter 0.00314561 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.00013583 +GaussianMLPPolicy/LossBefore -2.61466e-08 +GaussianMLPPolicy/dLoss -0.000135856 +Iteration 480 +MetaTest/Average/AverageDiscountedReturn -50.6371 +MetaTest/Average/AverageReturn -50.6371 +MetaTest/Average/Iteration 480 +MetaTest/Average/MaxReturn -40.1461 +MetaTest/Average/MinReturn -102.693 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 12.5815 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.6371 +MetaTest/__unnamed_task__/AverageReturn -50.6371 +MetaTest/__unnamed_task__/Iteration 480 +MetaTest/__unnamed_task__/MaxReturn -40.1461 +MetaTest/__unnamed_task__/MinReturn -102.693 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 12.5815 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3088e+07 +__unnamed_task__/AverageDiscountedReturn -25.119 +__unnamed_task__/AverageReturn -49.3903 +__unnamed_task__/Iteration 480 +__unnamed_task__/MaxReturn -37.3337 +__unnamed_task__/MinReturn -103.975 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 9.01486 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 12:55:49 | [maml_trainer] epoch #481 | Sampling for adapation and meta-testing... +2025-04-13 12:59:49 | [maml_trainer] epoch #481 | Finished meta-testing... +2025-04-13 12:59:50 | [maml_trainer] epoch #481 | Saving snapshot... +2025-04-13 13:00:12 | [maml_trainer] epoch #481 | Saved +2025-04-13 13:00:12 | [maml_trainer] epoch #481 | Time 850856.19 s +2025-04-13 13:00:12 | [maml_trainer] epoch #481 | EpochTime 1707.64 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.5102 +Average/AverageReturn -50.3003 +Average/Iteration 481 +Average/MaxReturn -39.2861 +Average/MinReturn -135.514 +Average/NumEpisodes 120 +Average/StdReturn 11.6343 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69303 +GaussianMLPPolicy/KLAfter 0.0023941 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 9.82202e-05 +GaussianMLPPolicy/LossBefore 9.33806e-09 +GaussianMLPPolicy/dLoss -9.82109e-05 +Iteration 481 +MetaTest/Average/AverageDiscountedReturn -50.4037 +MetaTest/Average/AverageReturn -50.4037 +MetaTest/Average/Iteration 481 +MetaTest/Average/MaxReturn -42.1529 +MetaTest/Average/MinReturn -74.8224 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 9.37635 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.4037 +MetaTest/__unnamed_task__/AverageReturn -50.4037 +MetaTest/__unnamed_task__/Iteration 481 +MetaTest/__unnamed_task__/MaxReturn -42.1529 +MetaTest/__unnamed_task__/MinReturn -74.8224 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 9.37635 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3136e+07 +__unnamed_task__/AverageDiscountedReturn -25.5102 +__unnamed_task__/AverageReturn -50.3003 +__unnamed_task__/Iteration 481 +__unnamed_task__/MaxReturn -39.2861 +__unnamed_task__/MinReturn -135.514 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.6343 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 13:24:19 | [maml_trainer] epoch #482 | Sampling for adapation and meta-testing... +2025-04-13 13:28:21 | [maml_trainer] epoch #482 | Finished meta-testing... +2025-04-13 13:28:21 | [maml_trainer] epoch #482 | Saving snapshot... +2025-04-13 13:28:42 | [maml_trainer] epoch #482 | Saved +2025-04-13 13:28:42 | [maml_trainer] epoch #482 | Time 852566.66 s +2025-04-13 13:28:42 | [maml_trainer] epoch #482 | EpochTime 1710.47 s +------------------------------------------------- ------------- +Average/AverageDiscountedReturn -24.7694 +Average/AverageReturn -48.5927 +Average/Iteration 482 +Average/MaxReturn -37.7682 +Average/MinReturn -68.2881 +Average/NumEpisodes 120 +Average/StdReturn 6.70435 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69423 +GaussianMLPPolicy/KLAfter 0.0025646 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -9.82452e-05 +GaussianMLPPolicy/LossBefore -7.62939e-09 +GaussianMLPPolicy/dLoss 9.82376e-05 +Iteration 482 +MetaTest/Average/AverageDiscountedReturn -47.4713 +MetaTest/Average/AverageReturn -47.4713 +MetaTest/Average/Iteration 482 +MetaTest/Average/MaxReturn -41.1449 +MetaTest/Average/MinReturn -62.7586 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.29534 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.4713 +MetaTest/__unnamed_task__/AverageReturn -47.4713 +MetaTest/__unnamed_task__/Iteration 482 +MetaTest/__unnamed_task__/MaxReturn -41.1449 +MetaTest/__unnamed_task__/MinReturn -62.7586 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.29534 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3184e+07 +__unnamed_task__/AverageDiscountedReturn -24.7694 +__unnamed_task__/AverageReturn -48.5927 +__unnamed_task__/Iteration 482 +__unnamed_task__/MaxReturn -37.7682 +__unnamed_task__/MinReturn -68.2881 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.70435 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- ------------- +2025-04-13 13:52:52 | [maml_trainer] epoch #483 | Sampling for adapation and meta-testing... +2025-04-13 13:56:56 | [maml_trainer] epoch #483 | Finished meta-testing... +2025-04-13 13:56:56 | [maml_trainer] epoch #483 | Saving snapshot... +2025-04-13 13:57:17 | [maml_trainer] epoch #483 | Saved +2025-04-13 13:57:17 | [maml_trainer] epoch #483 | Time 854281.29 s +2025-04-13 13:57:17 | [maml_trainer] epoch #483 | EpochTime 1714.63 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.1147 +Average/AverageReturn -49.6094 +Average/Iteration 483 +Average/MaxReturn -34.7636 +Average/MinReturn -137.547 +Average/NumEpisodes 120 +Average/StdReturn 12.9544 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69562 +GaussianMLPPolicy/KLAfter 0.00276083 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 6.00057e-05 +GaussianMLPPolicy/LossBefore -2.54313e-09 +GaussianMLPPolicy/dLoss -6.00082e-05 +Iteration 483 +MetaTest/Average/AverageDiscountedReturn -49.7532 +MetaTest/Average/AverageReturn -49.7532 +MetaTest/Average/Iteration 483 +MetaTest/Average/MaxReturn -39.1484 +MetaTest/Average/MinReturn -68.4788 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.94146 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.7532 +MetaTest/__unnamed_task__/AverageReturn -49.7532 +MetaTest/__unnamed_task__/Iteration 483 +MetaTest/__unnamed_task__/MaxReturn -39.1484 +MetaTest/__unnamed_task__/MinReturn -68.4788 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.94146 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3232e+07 +__unnamed_task__/AverageDiscountedReturn -25.1147 +__unnamed_task__/AverageReturn -49.6094 +__unnamed_task__/Iteration 483 +__unnamed_task__/MaxReturn -34.7636 +__unnamed_task__/MinReturn -137.547 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.9544 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 14:21:27 | [maml_trainer] epoch #484 | Sampling for adapation and meta-testing... +2025-04-13 14:25:24 | [maml_trainer] epoch #484 | Finished meta-testing... +2025-04-13 14:25:24 | [maml_trainer] epoch #484 | Saving snapshot... +2025-04-13 14:25:47 | [maml_trainer] epoch #484 | Saved +2025-04-13 14:25:47 | [maml_trainer] epoch #484 | Time 855991.09 s +2025-04-13 14:25:47 | [maml_trainer] epoch #484 | EpochTime 1709.79 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.7963 +Average/AverageReturn -48.7492 +Average/Iteration 484 +Average/MaxReturn -39.0258 +Average/MinReturn -146.362 +Average/NumEpisodes 120 +Average/StdReturn 11.7636 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69731 +GaussianMLPPolicy/KLAfter 0.00378086 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.000120675 +GaussianMLPPolicy/LossBefore 2.9405e-09 +GaussianMLPPolicy/dLoss 0.000120678 +Iteration 484 +MetaTest/Average/AverageDiscountedReturn -47.6939 +MetaTest/Average/AverageReturn -47.6939 +MetaTest/Average/Iteration 484 +MetaTest/Average/MaxReturn -40.4039 +MetaTest/Average/MinReturn -71.9115 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 7.22812 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -47.6939 +MetaTest/__unnamed_task__/AverageReturn -47.6939 +MetaTest/__unnamed_task__/Iteration 484 +MetaTest/__unnamed_task__/MaxReturn -40.4039 +MetaTest/__unnamed_task__/MinReturn -71.9115 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 7.22812 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.328e+07 +__unnamed_task__/AverageDiscountedReturn -24.7963 +__unnamed_task__/AverageReturn -48.7492 +__unnamed_task__/Iteration 484 +__unnamed_task__/MaxReturn -39.0258 +__unnamed_task__/MinReturn -146.362 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.7636 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 14:49:46 | [maml_trainer] epoch #485 | Sampling for adapation and meta-testing... +2025-04-13 14:53:47 | [maml_trainer] epoch #485 | Finished meta-testing... +2025-04-13 14:53:47 | [maml_trainer] epoch #485 | Saving snapshot... +2025-04-13 14:54:09 | [maml_trainer] epoch #485 | Saved +2025-04-13 14:54:09 | [maml_trainer] epoch #485 | Time 857693.66 s +2025-04-13 14:54:09 | [maml_trainer] epoch #485 | EpochTime 1702.57 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.5941 +Average/AverageReturn -48.7878 +Average/Iteration 485 +Average/MaxReturn -38.1195 +Average/MinReturn -137.349 +Average/NumEpisodes 120 +Average/StdReturn 11.7572 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69818 +GaussianMLPPolicy/KLAfter 0.00195634 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000120339 +GaussianMLPPolicy/LossBefore -1.20401e-08 +GaussianMLPPolicy/dLoss -0.000120351 +Iteration 485 +MetaTest/Average/AverageDiscountedReturn -46.653 +MetaTest/Average/AverageReturn -46.653 +MetaTest/Average/Iteration 485 +MetaTest/Average/MaxReturn -40.2031 +MetaTest/Average/MinReturn -63.4127 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 5.52831 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.653 +MetaTest/__unnamed_task__/AverageReturn -46.653 +MetaTest/__unnamed_task__/Iteration 485 +MetaTest/__unnamed_task__/MaxReturn -40.2031 +MetaTest/__unnamed_task__/MinReturn -63.4127 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 5.52831 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3328e+07 +__unnamed_task__/AverageDiscountedReturn -24.5941 +__unnamed_task__/AverageReturn -48.7878 +__unnamed_task__/Iteration 485 +__unnamed_task__/MaxReturn -38.1195 +__unnamed_task__/MinReturn -137.349 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.7572 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 15:18:34 | [maml_trainer] epoch #486 | Sampling for adapation and meta-testing... +2025-04-13 15:22:40 | [maml_trainer] epoch #486 | Finished meta-testing... +2025-04-13 15:22:40 | [maml_trainer] epoch #486 | Saving snapshot... +2025-04-13 15:23:02 | [maml_trainer] epoch #486 | Saved +2025-04-13 15:23:02 | [maml_trainer] epoch #486 | Time 859425.97 s +2025-04-13 15:23:02 | [maml_trainer] epoch #486 | EpochTime 1732.31 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.2746 +Average/AverageReturn -46.9807 +Average/Iteration 486 +Average/MaxReturn -37.344 +Average/MinReturn -156.203 +Average/NumEpisodes 120 +Average/StdReturn 11.5389 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69829 +GaussianMLPPolicy/KLAfter 0.00290714 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -0.00011594 +GaussianMLPPolicy/LossBefore 7.54992e-09 +GaussianMLPPolicy/dLoss 0.000115947 +Iteration 486 +MetaTest/Average/AverageDiscountedReturn -46.4597 +MetaTest/Average/AverageReturn -46.4597 +MetaTest/Average/Iteration 486 +MetaTest/Average/MaxReturn -37.8856 +MetaTest/Average/MinReturn -69.0323 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 6.29547 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.4597 +MetaTest/__unnamed_task__/AverageReturn -46.4597 +MetaTest/__unnamed_task__/Iteration 486 +MetaTest/__unnamed_task__/MaxReturn -37.8856 +MetaTest/__unnamed_task__/MinReturn -69.0323 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 6.29547 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3376e+07 +__unnamed_task__/AverageDiscountedReturn -24.2746 +__unnamed_task__/AverageReturn -46.9807 +__unnamed_task__/Iteration 486 +__unnamed_task__/MaxReturn -37.344 +__unnamed_task__/MinReturn -156.203 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 11.5389 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 15:47:25 | [maml_trainer] epoch #487 | Sampling for adapation and meta-testing... +2025-04-13 15:51:29 | [maml_trainer] epoch #487 | Finished meta-testing... +2025-04-13 15:51:29 | [maml_trainer] epoch #487 | Saving snapshot... +2025-04-13 15:51:50 | [maml_trainer] epoch #487 | Saved +2025-04-13 15:51:50 | [maml_trainer] epoch #487 | Time 861154.83 s +2025-04-13 15:51:50 | [maml_trainer] epoch #487 | EpochTime 1728.86 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -23.9875 +Average/AverageReturn -45.9283 +Average/Iteration 487 +Average/MaxReturn -33.8996 +Average/MinReturn -81.9916 +Average/NumEpisodes 120 +Average/StdReturn 6.71015 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69844 +GaussianMLPPolicy/KLAfter 0.0034377 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -2.99501e-05 +GaussianMLPPolicy/LossBefore -1.50998e-08 +GaussianMLPPolicy/dLoss 2.9935e-05 +Iteration 487 +MetaTest/Average/AverageDiscountedReturn -51.6614 +MetaTest/Average/AverageReturn -51.6614 +MetaTest/Average/Iteration 487 +MetaTest/Average/MaxReturn -33.9955 +MetaTest/Average/MinReturn -115.358 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 22.5854 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -51.6614 +MetaTest/__unnamed_task__/AverageReturn -51.6614 +MetaTest/__unnamed_task__/Iteration 487 +MetaTest/__unnamed_task__/MaxReturn -33.9955 +MetaTest/__unnamed_task__/MinReturn -115.358 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 22.5854 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3424e+07 +__unnamed_task__/AverageDiscountedReturn -23.9875 +__unnamed_task__/AverageReturn -45.9283 +__unnamed_task__/Iteration 487 +__unnamed_task__/MaxReturn -33.8996 +__unnamed_task__/MinReturn -81.9916 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 6.71015 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 16:16:13 | [maml_trainer] epoch #488 | Sampling for adapation and meta-testing... +2025-04-13 16:20:16 | [maml_trainer] epoch #488 | Finished meta-testing... +2025-04-13 16:20:16 | [maml_trainer] epoch #488 | Saving snapshot... +2025-04-13 16:20:38 | [maml_trainer] epoch #488 | Saved +2025-04-13 16:20:38 | [maml_trainer] epoch #488 | Time 862882.31 s +2025-04-13 16:20:38 | [maml_trainer] epoch #488 | EpochTime 1727.47 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.1356 +Average/AverageReturn -48.518 +Average/Iteration 488 +Average/MaxReturn -34.8822 +Average/MinReturn -140.795 +Average/NumEpisodes 120 +Average/StdReturn 16.9888 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69707 +GaussianMLPPolicy/KLAfter 0.00499524 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.50038e-05 +GaussianMLPPolicy/LossBefore -1.66893e-09 +GaussianMLPPolicy/dLoss 1.50021e-05 +Iteration 488 +MetaTest/Average/AverageDiscountedReturn -50.2408 +MetaTest/Average/AverageReturn -50.2408 +MetaTest/Average/Iteration 488 +MetaTest/Average/MaxReturn -36.5485 +MetaTest/Average/MinReturn -161.904 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 26.5133 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2408 +MetaTest/__unnamed_task__/AverageReturn -50.2408 +MetaTest/__unnamed_task__/Iteration 488 +MetaTest/__unnamed_task__/MaxReturn -36.5485 +MetaTest/__unnamed_task__/MinReturn -161.904 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 26.5133 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3472e+07 +__unnamed_task__/AverageDiscountedReturn -24.1356 +__unnamed_task__/AverageReturn -48.518 +__unnamed_task__/Iteration 488 +__unnamed_task__/MaxReturn -34.8822 +__unnamed_task__/MinReturn -140.795 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.9888 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 16:45:03 | [maml_trainer] epoch #489 | Sampling for adapation and meta-testing... +2025-04-13 16:49:05 | [maml_trainer] epoch #489 | Finished meta-testing... +2025-04-13 16:49:05 | [maml_trainer] epoch #489 | Saving snapshot... +2025-04-13 16:49:26 | [maml_trainer] epoch #489 | Saved +2025-04-13 16:49:26 | [maml_trainer] epoch #489 | Time 864610.71 s +2025-04-13 16:49:26 | [maml_trainer] epoch #489 | EpochTime 1728.40 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -23.6326 +Average/AverageReturn -46.9464 +Average/Iteration 489 +Average/MaxReturn -33.2619 +Average/MinReturn -147.941 +Average/NumEpisodes 120 +Average/StdReturn 16.289 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69689 +GaussianMLPPolicy/KLAfter 0.00383406 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -1.32259e-05 +GaussianMLPPolicy/LossBefore -5.64257e-09 +GaussianMLPPolicy/dLoss 1.32203e-05 +Iteration 489 +MetaTest/Average/AverageDiscountedReturn -54.3048 +MetaTest/Average/AverageReturn -54.3048 +MetaTest/Average/Iteration 489 +MetaTest/Average/MaxReturn -38.7283 +MetaTest/Average/MinReturn -150.558 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.143 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -54.3048 +MetaTest/__unnamed_task__/AverageReturn -54.3048 +MetaTest/__unnamed_task__/Iteration 489 +MetaTest/__unnamed_task__/MaxReturn -38.7283 +MetaTest/__unnamed_task__/MinReturn -150.558 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.143 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.352e+07 +__unnamed_task__/AverageDiscountedReturn -23.6326 +__unnamed_task__/AverageReturn -46.9464 +__unnamed_task__/Iteration 489 +__unnamed_task__/MaxReturn -33.2619 +__unnamed_task__/MinReturn -147.941 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 16.289 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 17:13:54 | [maml_trainer] epoch #490 | Sampling for adapation and meta-testing... +2025-04-13 17:17:59 | [maml_trainer] epoch #490 | Finished meta-testing... +2025-04-13 17:17:59 | [maml_trainer] epoch #490 | Saving snapshot... +2025-04-13 17:18:20 | [maml_trainer] epoch #490 | Saved +2025-04-13 17:18:20 | [maml_trainer] epoch #490 | Time 866344.54 s +2025-04-13 17:18:20 | [maml_trainer] epoch #490 | EpochTime 1733.83 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.4125 +Average/AverageReturn -50.6142 +Average/Iteration 490 +Average/MaxReturn -34.8146 +Average/MinReturn -157.415 +Average/NumEpisodes 120 +Average/StdReturn 23.3176 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69672 +GaussianMLPPolicy/KLAfter 0.00390165 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 0.000134698 +GaussianMLPPolicy/LossBefore 3.0299e-09 +GaussianMLPPolicy/dLoss -0.000134695 +Iteration 490 +MetaTest/Average/AverageDiscountedReturn -46.7207 +MetaTest/Average/AverageReturn -46.7207 +MetaTest/Average/Iteration 490 +MetaTest/Average/MaxReturn -37.5499 +MetaTest/Average/MinReturn -103.029 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 14.0247 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -46.7207 +MetaTest/__unnamed_task__/AverageReturn -46.7207 +MetaTest/__unnamed_task__/Iteration 490 +MetaTest/__unnamed_task__/MaxReturn -37.5499 +MetaTest/__unnamed_task__/MinReturn -103.029 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 14.0247 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3568e+07 +__unnamed_task__/AverageDiscountedReturn -24.4125 +__unnamed_task__/AverageReturn -50.6142 +__unnamed_task__/Iteration 490 +__unnamed_task__/MaxReturn -34.8146 +__unnamed_task__/MinReturn -157.415 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 23.3176 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 17:43:02 | [maml_trainer] epoch #491 | Sampling for adapation and meta-testing... +2025-04-13 17:47:06 | [maml_trainer] epoch #491 | Finished meta-testing... +2025-04-13 17:47:06 | [maml_trainer] epoch #491 | Saving snapshot... +2025-04-13 17:47:28 | [maml_trainer] epoch #491 | Saved +2025-04-13 17:47:28 | [maml_trainer] epoch #491 | Time 868091.98 s +2025-04-13 17:47:28 | [maml_trainer] epoch #491 | EpochTime 1747.43 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.2827 +Average/AverageReturn -51.1435 +Average/Iteration 491 +Average/MaxReturn -34.2685 +Average/MinReturn -164.861 +Average/NumEpisodes 120 +Average/StdReturn 24.9581 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69699 +GaussianMLPPolicy/KLAfter 0.00403642 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -5.16093e-05 +GaussianMLPPolicy/LossBefore 2.00669e-09 +GaussianMLPPolicy/dLoss 5.16113e-05 +Iteration 491 +MetaTest/Average/AverageDiscountedReturn -42.1084 +MetaTest/Average/AverageReturn -42.1084 +MetaTest/Average/Iteration 491 +MetaTest/Average/MaxReturn -34.3941 +MetaTest/Average/MinReturn -49.0909 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 3.60757 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -42.1084 +MetaTest/__unnamed_task__/AverageReturn -42.1084 +MetaTest/__unnamed_task__/Iteration 491 +MetaTest/__unnamed_task__/MaxReturn -34.3941 +MetaTest/__unnamed_task__/MinReturn -49.0909 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 3.60757 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3616e+07 +__unnamed_task__/AverageDiscountedReturn -24.2827 +__unnamed_task__/AverageReturn -51.1435 +__unnamed_task__/Iteration 491 +__unnamed_task__/MaxReturn -34.2685 +__unnamed_task__/MinReturn -164.861 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 24.9581 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 18:12:05 | [maml_trainer] epoch #492 | Sampling for adapation and meta-testing... +2025-04-13 18:16:10 | [maml_trainer] epoch #492 | Finished meta-testing... +2025-04-13 18:16:10 | [maml_trainer] epoch #492 | Saving snapshot... +2025-04-13 18:16:33 | [maml_trainer] epoch #492 | Saved +2025-04-13 18:16:33 | [maml_trainer] epoch #492 | Time 869837.02 s +2025-04-13 18:16:33 | [maml_trainer] epoch #492 | EpochTime 1745.04 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.441 +Average/AverageReturn -51.7723 +Average/Iteration 492 +Average/MaxReturn 19.4298 +Average/MinReturn -167.739 +Average/NumEpisodes 120 +Average/StdReturn 26.3526 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69664 +GaussianMLPPolicy/KLAfter 0.00370771 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 2.34492e-05 +GaussianMLPPolicy/LossBefore 3.88424e-09 +GaussianMLPPolicy/dLoss -2.34453e-05 +Iteration 492 +MetaTest/Average/AverageDiscountedReturn -58.2623 +MetaTest/Average/AverageReturn -58.2623 +MetaTest/Average/Iteration 492 +MetaTest/Average/MaxReturn -37.2367 +MetaTest/Average/MinReturn -138.754 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 28.3935 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.2623 +MetaTest/__unnamed_task__/AverageReturn -58.2623 +MetaTest/__unnamed_task__/Iteration 492 +MetaTest/__unnamed_task__/MaxReturn -37.2367 +MetaTest/__unnamed_task__/MinReturn -138.754 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 28.3935 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3664e+07 +__unnamed_task__/AverageDiscountedReturn -24.441 +__unnamed_task__/AverageReturn -51.7723 +__unnamed_task__/Iteration 492 +__unnamed_task__/MaxReturn 19.4298 +__unnamed_task__/MinReturn -167.739 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.3526 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 18:41:17 | [maml_trainer] epoch #493 | Sampling for adapation and meta-testing... +2025-04-13 18:45:20 | [maml_trainer] epoch #493 | Finished meta-testing... +2025-04-13 18:45:20 | [maml_trainer] epoch #493 | Saving snapshot... +2025-04-13 18:45:42 | [maml_trainer] epoch #493 | Saved +2025-04-13 18:45:42 | [maml_trainer] epoch #493 | Time 871586.62 s +2025-04-13 18:45:42 | [maml_trainer] epoch #493 | EpochTime 1749.59 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.2471 +Average/AverageReturn -55.5879 +Average/Iteration 493 +Average/MaxReturn -35.3932 +Average/MinReturn -157.848 +Average/NumEpisodes 120 +Average/StdReturn 30.3456 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69632 +GaussianMLPPolicy/KLAfter 0.00292 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.02766e-05 +GaussianMLPPolicy/LossBefore -3.29812e-09 +GaussianMLPPolicy/dLoss 4.02733e-05 +Iteration 493 +MetaTest/Average/AverageDiscountedReturn -58.3316 +MetaTest/Average/AverageReturn -58.3316 +MetaTest/Average/Iteration 493 +MetaTest/Average/MaxReturn -38.2442 +MetaTest/Average/MinReturn -127.134 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 25.1011 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -58.3316 +MetaTest/__unnamed_task__/AverageReturn -58.3316 +MetaTest/__unnamed_task__/Iteration 493 +MetaTest/__unnamed_task__/MaxReturn -38.2442 +MetaTest/__unnamed_task__/MinReturn -127.134 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 25.1011 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3712e+07 +__unnamed_task__/AverageDiscountedReturn -25.2471 +__unnamed_task__/AverageReturn -55.5879 +__unnamed_task__/Iteration 493 +__unnamed_task__/MaxReturn -35.3932 +__unnamed_task__/MinReturn -157.848 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 30.3456 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 19:10:14 | [maml_trainer] epoch #494 | Sampling for adapation and meta-testing... +2025-04-13 19:14:22 | [maml_trainer] epoch #494 | Finished meta-testing... +2025-04-13 19:14:22 | [maml_trainer] epoch #494 | Saving snapshot... +2025-04-13 19:14:44 | [maml_trainer] epoch #494 | Saved +2025-04-13 19:14:44 | [maml_trainer] epoch #494 | Time 873328.93 s +2025-04-13 19:14:44 | [maml_trainer] epoch #494 | EpochTime 1742.31 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -25.4783 +Average/AverageReturn -56.9623 +Average/Iteration 494 +Average/MaxReturn -35.6629 +Average/MinReturn -174.382 +Average/NumEpisodes 120 +Average/StdReturn 33.1153 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.6953 +GaussianMLPPolicy/KLAfter 0.00196831 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 1.17921e-06 +GaussianMLPPolicy/LossBefore -9.73542e-10 +GaussianMLPPolicy/dLoss -1.18018e-06 +Iteration 494 +MetaTest/Average/AverageDiscountedReturn -53.9928 +MetaTest/Average/AverageReturn -53.9928 +MetaTest/Average/Iteration 494 +MetaTest/Average/MaxReturn -36.2099 +MetaTest/Average/MinReturn -152.379 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 31.3183 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -53.9928 +MetaTest/__unnamed_task__/AverageReturn -53.9928 +MetaTest/__unnamed_task__/Iteration 494 +MetaTest/__unnamed_task__/MaxReturn -36.2099 +MetaTest/__unnamed_task__/MinReturn -152.379 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 31.3183 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.376e+07 +__unnamed_task__/AverageDiscountedReturn -25.4783 +__unnamed_task__/AverageReturn -56.9623 +__unnamed_task__/Iteration 494 +__unnamed_task__/MaxReturn -35.6629 +__unnamed_task__/MinReturn -174.382 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 33.1153 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 19:38:52 | [maml_trainer] epoch #495 | Sampling for adapation and meta-testing... +2025-04-13 19:42:53 | [maml_trainer] epoch #495 | Finished meta-testing... +2025-04-13 19:42:53 | [maml_trainer] epoch #495 | Saving snapshot... +2025-04-13 19:43:15 | [maml_trainer] epoch #495 | Saved +2025-04-13 19:43:15 | [maml_trainer] epoch #495 | Time 875039.40 s +2025-04-13 19:43:15 | [maml_trainer] epoch #495 | EpochTime 1710.47 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.5992 +Average/AverageReturn -50.8746 +Average/Iteration 495 +Average/MaxReturn -35.1535 +Average/MinReturn -157.302 +Average/NumEpisodes 120 +Average/StdReturn 23.2235 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69339 +GaussianMLPPolicy/KLAfter 0.00161742 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -4.7699e-05 +GaussianMLPPolicy/LossBefore 4.29153e-09 +GaussianMLPPolicy/dLoss 4.77032e-05 +Iteration 495 +MetaTest/Average/AverageDiscountedReturn -49.2652 +MetaTest/Average/AverageReturn -49.2652 +MetaTest/Average/Iteration 495 +MetaTest/Average/MaxReturn -36.3411 +MetaTest/Average/MinReturn -133.458 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 20.1406 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -49.2652 +MetaTest/__unnamed_task__/AverageReturn -49.2652 +MetaTest/__unnamed_task__/Iteration 495 +MetaTest/__unnamed_task__/MaxReturn -36.3411 +MetaTest/__unnamed_task__/MinReturn -133.458 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 20.1406 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3808e+07 +__unnamed_task__/AverageDiscountedReturn -24.5992 +__unnamed_task__/AverageReturn -50.8746 +__unnamed_task__/Iteration 495 +__unnamed_task__/MaxReturn -35.1535 +__unnamed_task__/MinReturn -157.302 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 23.2235 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 20:07:27 | [maml_trainer] epoch #496 | Sampling for adapation and meta-testing... +2025-04-13 20:11:28 | [maml_trainer] epoch #496 | Finished meta-testing... +2025-04-13 20:11:28 | [maml_trainer] epoch #496 | Saving snapshot... +2025-04-13 20:11:51 | [maml_trainer] epoch #496 | Saved +2025-04-13 20:11:51 | [maml_trainer] epoch #496 | Time 876755.10 s +2025-04-13 20:11:51 | [maml_trainer] epoch #496 | EpochTime 1715.69 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -23.8107 +Average/AverageReturn -47.8101 +Average/Iteration 496 +Average/MaxReturn -28.4616 +Average/MinReturn -146.148 +Average/NumEpisodes 120 +Average/StdReturn 20.6118 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.69107 +GaussianMLPPolicy/KLAfter 0.0016981 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -3.73617e-06 +GaussianMLPPolicy/LossBefore 3.67562e-09 +GaussianMLPPolicy/dLoss 3.73984e-06 +Iteration 496 +MetaTest/Average/AverageDiscountedReturn -45.8328 +MetaTest/Average/AverageReturn -45.8328 +MetaTest/Average/Iteration 496 +MetaTest/Average/MaxReturn -35.4434 +MetaTest/Average/MinReturn -113.537 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 16.0447 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -45.8328 +MetaTest/__unnamed_task__/AverageReturn -45.8328 +MetaTest/__unnamed_task__/Iteration 496 +MetaTest/__unnamed_task__/MaxReturn -35.4434 +MetaTest/__unnamed_task__/MinReturn -113.537 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 16.0447 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3856e+07 +__unnamed_task__/AverageDiscountedReturn -23.8107 +__unnamed_task__/AverageReturn -47.8101 +__unnamed_task__/Iteration 496 +__unnamed_task__/MaxReturn -28.4616 +__unnamed_task__/MinReturn -146.148 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 20.6118 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 20:42:46 | [maml_trainer] epoch #497 | Sampling for adapation and meta-testing... +2025-04-13 20:48:37 | [maml_trainer] epoch #497 | Finished meta-testing... +2025-04-13 20:48:37 | [maml_trainer] epoch #497 | Saving snapshot... +2025-04-13 20:49:11 | [maml_trainer] epoch #497 | Saved +2025-04-13 20:49:11 | [maml_trainer] epoch #497 | Time 878995.55 s +2025-04-13 20:49:11 | [maml_trainer] epoch #497 | EpochTime 2240.44 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.8921 +Average/AverageReturn -51.2775 +Average/Iteration 497 +Average/MaxReturn -33.9596 +Average/MinReturn -160.212 +Average/NumEpisodes 120 +Average/StdReturn 26.147 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68863 +GaussianMLPPolicy/KLAfter 0.00136542 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -6.95573e-05 +GaussianMLPPolicy/LossBefore -1.19209e-09 +GaussianMLPPolicy/dLoss 6.95561e-05 +Iteration 497 +MetaTest/Average/AverageDiscountedReturn -55.3159 +MetaTest/Average/AverageReturn -55.3159 +MetaTest/Average/Iteration 497 +MetaTest/Average/MaxReturn -35.7941 +MetaTest/Average/MinReturn -145.094 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 30.6329 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -55.3159 +MetaTest/__unnamed_task__/AverageReturn -55.3159 +MetaTest/__unnamed_task__/Iteration 497 +MetaTest/__unnamed_task__/MaxReturn -35.7941 +MetaTest/__unnamed_task__/MinReturn -145.094 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 30.6329 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3904e+07 +__unnamed_task__/AverageDiscountedReturn -24.8921 +__unnamed_task__/AverageReturn -51.2775 +__unnamed_task__/Iteration 497 +__unnamed_task__/MaxReturn -33.9596 +__unnamed_task__/MinReturn -160.212 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.147 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 21:24:18 | [maml_trainer] epoch #498 | Sampling for adapation and meta-testing... +2025-04-13 21:30:11 | [maml_trainer] epoch #498 | Finished meta-testing... +2025-04-13 21:30:11 | [maml_trainer] epoch #498 | Saving snapshot... +2025-04-13 21:30:44 | [maml_trainer] epoch #498 | Saved +2025-04-13 21:30:44 | [maml_trainer] epoch #498 | Time 881488.15 s +2025-04-13 21:30:44 | [maml_trainer] epoch #498 | EpochTime 2492.60 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -24.0413 +Average/AverageReturn -49.7993 +Average/Iteration 498 +Average/MaxReturn -33.9479 +Average/MinReturn -175.834 +Average/NumEpisodes 120 +Average/StdReturn 26.3871 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68673 +GaussianMLPPolicy/KLAfter 0.00245724 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter -8.12384e-05 +GaussianMLPPolicy/LossBefore -5.46376e-09 +GaussianMLPPolicy/dLoss 8.12329e-05 +Iteration 498 +MetaTest/Average/AverageDiscountedReturn -50.282 +MetaTest/Average/AverageReturn -50.282 +MetaTest/Average/Iteration 498 +MetaTest/Average/MaxReturn -37.1169 +MetaTest/Average/MinReturn -117.78 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 17.37 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.282 +MetaTest/__unnamed_task__/AverageReturn -50.282 +MetaTest/__unnamed_task__/Iteration 498 +MetaTest/__unnamed_task__/MaxReturn -37.1169 +MetaTest/__unnamed_task__/MinReturn -117.78 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 17.37 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.3952e+07 +__unnamed_task__/AverageDiscountedReturn -24.0413 +__unnamed_task__/AverageReturn -49.7993 +__unnamed_task__/Iteration 498 +__unnamed_task__/MaxReturn -33.9479 +__unnamed_task__/MinReturn -175.834 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 26.3871 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- -------------- +2025-04-13 22:05:50 | [maml_trainer] epoch #499 | Sampling for adapation and meta-testing... +2025-04-13 22:11:42 | [maml_trainer] epoch #499 | Finished meta-testing... +2025-04-13 22:11:42 | [maml_trainer] epoch #499 | Saving snapshot... +2025-04-13 22:12:16 | [maml_trainer] epoch #499 | Saved +2025-04-13 22:12:16 | [maml_trainer] epoch #499 | Time 883980.16 s +2025-04-13 22:12:16 | [maml_trainer] epoch #499 | EpochTime 2492.01 s +------------------------------------------------- -------------- +Average/AverageDiscountedReturn -23.4739 +Average/AverageReturn -45.2006 +Average/Iteration 499 +Average/MaxReturn -35.0396 +Average/MinReturn -135.32 +Average/NumEpisodes 120 +Average/StdReturn 12.958 +Average/TerminationRate 0 +GaussianMLPPolicy/Entropy 9.68443 +GaussianMLPPolicy/KLAfter 0.00337118 +GaussianMLPPolicy/KLBefore 0 +GaussianMLPPolicy/LossAfter 8.81191e-05 +GaussianMLPPolicy/LossBefore -3.13918e-09 +GaussianMLPPolicy/dLoss -8.81223e-05 +Iteration 499 +MetaTest/Average/AverageDiscountedReturn -50.2644 +MetaTest/Average/AverageReturn -50.2644 +MetaTest/Average/Iteration 499 +MetaTest/Average/MaxReturn -36.6546 +MetaTest/Average/MinReturn -150.917 +MetaTest/Average/NumEpisodes 20 +MetaTest/Average/StdReturn 23.6726 +MetaTest/Average/TerminationRate 0 +MetaTest/__unnamed_task__/AverageDiscountedReturn -50.2644 +MetaTest/__unnamed_task__/AverageReturn -50.2644 +MetaTest/__unnamed_task__/Iteration 499 +MetaTest/__unnamed_task__/MaxReturn -36.6546 +MetaTest/__unnamed_task__/MinReturn -150.917 +MetaTest/__unnamed_task__/NumEpisodes 20 +MetaTest/__unnamed_task__/StdReturn 23.6726 +MetaTest/__unnamed_task__/TerminationRate 0 +TotalEnvSteps 2.4e+07 +__unnamed_task__/AverageDiscountedReturn -23.4739 +__unnamed_task__/AverageReturn -45.2006 +__unnamed_task__/Iteration 499 +__unnamed_task__/MaxReturn -35.0396 +__unnamed_task__/MinReturn -135.32 +__unnamed_task__/NumEpisodes 120 +__unnamed_task__/StdReturn 12.958 +__unnamed_task__/TerminationRate 0 +------------------------------------------------- --------------